Best Open-Source Coding Agents
This page compares open-source coding agents: AI coding tools whose own source code is published under a licence approved by the Open Source Initiative (OSI), so that anyone can read, modify and redistribute the agent itself. As of 19 November 2026 it profiles thirteen actively released agents that passed the inclusion criteria set out below: opencode, Codex CLI, Pi, Gemini CLI, OpenHands, Cline, goose, Aider, Qwen Code, Kilo Code, mini-swe-agent, Kimi Code CLI and Mistral Vibe. All thirteen use the MIT License or the Apache License 2.0, both of which are on the OSI's list of approved licences. [1] The tables below order them by GitHub stars on that date, which is a count of bookmarks and not a measure of quality. The page does not rank the tools or recommend one of them.
This page is about the software that drives a model (the harness), not about the models. "Open source" here describes the agent's code only. The models an agent calls are a separate question: a model with downloadable weights is called open-weight on this wiki, and an open-source agent can just as well be pointed at a closed, hosted model. Several well-known agents publish some code or a public repository without an open-source licence; they are listed separately under Not open source with the licence they actually use. For a comparison that includes proprietary tools and prices, see Best AI Coding Assistants; for background on what a coding agent is, see that article.
How the tools were selected
Nothing on this page is an editorial ranking. The criteria below are this article's own inclusion rules, not an external standard. A tool is in the main table only if it passed three checks, all made on 19 November 2026:
- Licence. The LICENSE file in the project's current repository is an OSI-approved licence that covers the agent itself. [1] Repository moves were followed:
sst/opencodenow resolves toanomalyco/opencode,block/goosetoaaif-goose/goose,All-Hands-AI/OpenHandstoOpenHands/OpenHands, andbadlogic/pi-monotoearendil-works/pi. [2][4][6][8] - Maintenance. The repository is not archived, its README does not declare the project shut down, unmaintained or superseded, and a release was published in the twelve months before 19 November 2026.
- Adoption. The repository has at least 5,000 GitHub stars. Stars are used only as a documented threshold of public interest.
The main table is limited to the projects reviewed for this article. It is not a census of every project that would pass the three checks. Two projects that passed them on the same date but are not profiled here are Open Interpreter, whose README calls it "a fork of OpenAI's Codex" (Apache-2.0; release rust-v0.0.61 on 11 November 2026; 68,910 stars), and Forge (tailcallhq/forgecode; Apache-2.0; v2.14.0 on 1 October 2026; 7,635 stars). [83][84] Freebuff (CodebuffAI/freebuff; Apache-2.0; 14,233 stars) publishes no GitHub releases and was not assessed against the maintenance check. [85]
Projects that pass the licence check but fail the maintenance check are in Archived, superseded or unmaintained projects. Editors and terminals that contain an agent are in Editors and terminals with a built-in agent. Benchmark figures are quoted only from the benchmark's own leaderboard, with the date, the model and the harness version where the source gives one. None of these tools was installed or run for this article; every statement comes from the project's repository, its documentation or a published advisory.
Comparison table
Licence, release and star figures come from each repository and the GitHub API on 19 November 2026. "Latest release" is the newest non-prerelease tag for the agent itself.
| Tool | Licence | Maintainer | Interface | Latest release | GitHub stars (2026-11-19) |
|---|---|---|---|---|---|
| opencode | MIT | Anomaly (anomalyco) | Terminal, desktop app (beta) | v2.3.2, 2026-11-18 (1.x line: v1.19.6, 2026-11-17) | 227,832 [2] |
| Codex CLI | Apache-2.0 | OpenAI | Terminal | 0.170.0, 2026-11-18 | 135,798 [3] |
| Pi | MIT | Earendil Inc. | Terminal, RPC, TypeScript SDK | v1.5.2, 2026-11-10 | 122,758 [4] |
| Gemini CLI | Apache-2.0 | Terminal | v0.68.0, 2026-11-10 | 108,925 [5] | |
| OpenHands | MIT | OpenHands | Self-hosted web UI (Agent Canvas), SDK | v1.42.0, 2026-11-18 | 93,768 [6] |
| Cline | Apache-2.0 | Cline Bot Inc. | VS Code extension, CLI, desktop app, SDK | v4.1.26, 2026-10-26 | 71,758 [7] |
| goose | Apache-2.0 | Agentic AI Foundation (Linux Foundation) | Desktop app, CLI, API | v1.60.1, 2026-11-18 | 56,765 [8] |
| Aider | Apache-2.0 | Aider-AI | Terminal | 0.86.2 on PyPI, 2026-02-12 | 50,171 [9][15] |
| Qwen Code | Apache-2.0 | Qwen team (QwenLM) | Terminal, desktop app, Web UI (experimental), IDE plugins, SDKs | v0.28.0, 2026-11-17 | 30,764 [10] |
| Kilo Code | MIT | Kilo Code (Anaconda announced its acquisition on 15 July 2026) | VS Code extension, JetBrains plugin, CLI | v7.8.27, 2026-11-05 | 28,052 [11][66] |
| mini-swe-agent | MIT | Princeton and Stanford researchers | Terminal, Python library | v2.4.6, 2026-07-23 | 9,759 [12] |
| Kimi Code CLI | MIT | Moonshot AI | Terminal | 2.6.3, 2026-11-17 | 8,253 [13] |
| Mistral Vibe | Apache-2.0 | Mistral AI | Terminal | v3.1.3, 2026-11-18 | 5,424 [14] |
Five rows need a caveat. Aider's newest GitHub release is v0.86.0 (9 August 2025), its newest PyPI release is 0.86.2 (12 February 2026), and the last commit on its default branch was on 22 May 2026, so it is the least recently updated tool in the table. [9][15] The OpenHands/OpenHands repository now holds Agent Canvas, a control centre that runs the OpenHands agent and third-party agents; the agent, tools and server live in OpenHands/software-agent-sdk, also under the MIT License (v1.62.0, 11 November 2026). [6][16] Cline's README states that its JetBrains plugin is not open-sourced, so the Apache-2.0 licence covers the SDK, CLI, VS Code extension and desktop app but not that plugin. [7] Kilo's MIT licence covers the Kilo-Org/kilocode repository, which holds the VS Code extension, the JetBrains plugin and the CLI; Kilo's cloud platform and its desktop app are in separate repositories, Kilo-Org/cloud and Kilo-Org/kilo-desktop, under the Open Core Ventures Source Available License version 1.0, which is not on the OSI's list. [1][11][81][82] The opencode repository also bundles Figma skill files that are third-party material; their notice says "OpenCode's MIT license does not relicense them". [88]
What each tool is
| Tool | Summary from the current README |
|---|---|
| opencode | Terminal agent with two built-in agents, build (full access) and plan (read-only, denies edits by default), plus a general subagent [2] |
| Codex CLI | OpenAI's terminal agent; sign in with a ChatGPT plan or use an API key. The README points to a separate IDE extension, desktop app and cloud agent [3] |
| Pi | A "minimal, extensible agent harness" customised through extensions, skills, prompt templates and themes; it leaves out sub-agents and plan mode by design [4] |
| Gemini CLI | Maintained for Gemini Code Assist Standard and Enterprise licences; free individual access and the Google AI Pro and Ultra plans moved to the Antigravity CLI, which is not open source, on 18 June 2026 [5][34] |
| OpenHands | Runs agents locally, in Docker containers, on virtual machines or in the vendor's cloud, with scheduled and webhook-triggered automations [6] |
| Cline | Plan and Act modes, checkpoints, .clinerules files, Model Context Protocol servers, multi-agent teams, scheduled agents and a headless mode for CI [7] |
| goose | General-purpose local agent written in Rust with more than 15 model providers and more than 70 MCP extensions [8] |
| Aider | Pair programmer that builds a map of the repository and commits each change to git with a generated message [9] |
| Qwen Code | Multi-protocol agent that began as a fork of Gemini CLI v0.8.2 and stopped syncing with it from Qwen Code v0.1 [10] |
| Kilo Code | Code, Plan, Ask and Debug agents, inline autocomplete and a marketplace; its CLI is a fork of opencode [11] |
| mini-swe-agent | An agent class of about 100 lines of Python whose only tool is bash; the harness behind the SWE-bench "Bash Only" leaderboard [12][38] |
| Kimi Code CLI | Single-binary terminal agent with video input that speaks the Agent Client Protocol to editors [13] |
| Mistral Vibe | Terminal agent that asks before risky actions; the project takes bug reports but does not accept pull requests [14] |
Editors and terminals with a built-in agent
Two open-source developer tools are larger than a coding agent but ship one. They are listed apart from the main table because the agent is one feature of a larger program.
| Tool | Licence | Maintainer | Agent | Latest release | GitHub stars (2026-11-19) |
|---|---|---|---|---|---|
| Zed | GPL-3.0-or-later, with Apache-2.0 components | Zed Industries | First-party agent in the Agent Panel; external agents connect through the Agent Client Protocol [78] | v1.29.2, 2026-11-18 | 95,289 [17] |
| Warp | AGPL-3.0, with the UI framework crates under MIT | Warp | Built-in coding agent; can also host other CLI agents | v0.2026.06.03.09.49.stable_00, 2026-06-03 (newest stable release published on GitHub; the repository was last pushed on 2026-11-18) | 66,058 [18] |
Zed's README says its source is "licensed primarily under GPL-3.0-or-later, with Apache-2.0 components where marked". [17] Warp announced on 28 April 2026 that its client was now open source; the repository's licensing section puts the warpui_core and warpui crates under MIT and the rest under the AGPL v3. [18][19] Both the GNU General Public License version 3 and the GNU Affero General Public License version 3 are on the OSI's list of approved licences. [1] How their conditions differ from those of MIT and Apache-2.0 is explained in copyleft.
Archived, superseded or unmaintained projects
These projects carry an OSI-approved licence, so the code can still be forked, but each fails the maintenance check: the repository is archived, the README declares the project unmaintained or superseded, or no release was published in the twelve months before 19 November 2026.
| Project | Licence | Status on 2026-11-19 | Last release | Stars |
|---|---|---|---|---|
| Roo Code | Apache-2.0 | Repository archived; README says the extension "was shut down on May 15th" and points to the community fork ZooCode and to Cline | v3.54.0, 2026-05-15 | 24,238 [20][21] |
| Continue | Apache-2.0 | README: the repository "is no longer actively maintained and is read-only for all users" | 2.0.0 (tag v2.0.0-vscode, 2026-06-19) | 36,512 [23] |
| SWE-agent | MIT | README: "Most of our current development effort is on mini-swe-agent, which has superseded SWE-agent" | v1.1.0, 2025-05-22 | 20,829 [25] |
| Plandex | MIT | No release in the previous twelve months; last commit on the default branch 2025-10-03; README says Plandex Cloud is winding down | cli/v2.2.1, 2025-07-16 | 15,923 [26] |
| Void | Apache-2.0 | Repository archived; README: "Void is deprecated and no longer accepting contributions" | v1.3.4, 2025-04-15 (marked as a pre-release) | 28,707 [27] |
OpenCode (Go, opencode-ai/opencode) | MIT | Archived; README says the project "has continued under the name Crush" | v0.0.55, 2025-06-27 | 13,917 [28] |
| Kimi CLI (Python) | Apache-2.0 | Archived; description points to Kimi Code CLI | 1.52.0, 2026-09-22 | 11,410 [29] |
ZooCode, the fork that the Roo Code notice recommends, is published at Zoo-Code-Org/Zoo-Code under Apache-2.0; its latest release was v3.98.0 on 15 November 2026 and it had 2,135 stars, below this page's adoption threshold. [22]
Not open source
The tools below are often discussed alongside open-source agents. Each has a public repository or a published component, but the licence is not OSI-approved, or the repository contains no source code. The right-hand column quotes or summarises the licence file or README and adds nothing to it.
| Tool | Licence as published | What the licence file or README says |
|---|---|---|
| Crush (Charm) | Functional Source License, Version 1.1, MIT Future License (FSL-1.1-MIT) | "A Permitted Purpose is any purpose other than a Competing Use." The licence also grants "an additional license to use the Software under the MIT license that is effective on the second anniversary of the date we make the Software available" [30] |
| Claude Code | LICENSE.md, in full: "© Anthropic PBC. All rights reserved. Use is subject to Anthropic's Commercial Terms of Service." | The repository has no other licence file [32] |
| GitHub Copilot CLI | GitHub Copilot CLI License | Grants a licence "to install and run copies of the GitHub Copilot CLI" and to "reproduce and redistribute unmodified copies of the Software as part of an application or service", not on a standalone basis; it does not grant the right to "Modify, adapt, translate, or create derivative works of the Software" [33] |
| Antigravity CLI (Google) | No licence file | The repository holds a README, a changelog and example scripts, not the program's source; the README links Google's terms of service for the product [34] |
| Tabby | Apache 2.0, except the ee/ directory, which is under "The Tabby Enterprise license" | The root LICENSE says content under ee/ is licensed under the licence defined in ee/LICENSE; that file says the software "may only be used in production" under TabbyML's subscription terms with a valid Tabby Enterprise licence [35][87] |
| Cline JetBrains plugin | Source not published | The Cline README's product index says: "Currently we are not open-sourcing JetBrains plugins" [7] |
| Kilo cloud platform and Kilo Desktop | Open Core Ventures Source Available License (OCVSAL) version 1.0 | "Using software and associated documentation files (the "Software") in production requires a valid commercial agreement from the copyright holder." [81][82] |
The Functional Source License is not on the OSI's list of approved licences, and its own site describes it as "a Fair Source license that converts to Apache 2.0 or MIT after two years". [1][31] The archived Go OpenCode repository, whose README says the project continued as Crush, is under the MIT License; Crush's licence file is FSL-1.1-MIT. [28][30] Licences that publish source code without meeting the OSI's definition are covered in source-available. The arrangement in which a company publishes a core under an open-source licence and keeps other parts closed is described in open core; the general differences between licence families are covered in open-source license.
Published benchmark results
Benchmark scores for coding agents measure an agent and a model together, and each leaderboard uses its own tasks, time limits and model versions. Figures from different leaderboards, different versions of one leaderboard, or different models are not comparable with each other, and none of the numbers below should be read as a ranking of the tools on this page.
Terminal-Bench 4.1
Terminal-Bench scores agent and model pairs on command-line tasks. Version 4.1 was published on 9 November 2026 with hardened task verifiers; its maintainers re-graded the 4.0 submissions and say all scores stayed within the previously reported 95% confidence intervals. [37] On 19 November 2026 the public 4.1 leaderboard listed 52 entries for seven agents: GitHub Copilot, Claude Code, Antigravity CLI, Codex, Muse Code, Grok Build and mini-swe-agent (two of its eleven entries are spelled "mini-SWE-agent"). [36] Two of those names correspond to tools in this page's main table. The board's "Codex" entries link to OpenAI's Codex product page and do not say which Codex client or version was run; the mini-swe-agent entries link to that project's repository or website. [36] The rows below are the two highest entries under each of the two names:
| Agent as listed | Model (effort) | Resolution rate (± 95% confidence interval) | Release date shown | Source |
|---|---|---|---|---|
| Codex | GPT-6.2 Astra (max) | 62.1% ± 2.3 | 2026-11-17 | [36] |
| Codex | GPT-6.2 Sol (max) | 61.5% ± 2.8 | 2026-11-17 | [36] |
| mini-swe-agent | MiMo V2.6 Pro (none) | 27.0% ± 3.6 | 2026-09-22 | [36] |
| mini-swe-agent | Ember-1 (none) | 21.8% ± 3.5 | 2026-09-24 | [36] |
The leaderboard table names the agent but not its version, and the highest entry overall on that date was GitHub Copilot with Copilot Fusion (max) at 71.2% ± 2.9. [36] The Codex and mini-swe-agent rows use different models, so the gap between them says nothing about the two harnesses. The other eleven tools in the main table had no entry. Gemini CLI's own README tells readers not to use it to benchmark Gemini models, because its harness is not tuned for the Gemini 4 series. [5]
SWE-bench Verified
SWE-bench Verified is a 500-task, human-filtered subset of SWE-bench, which is built from real GitHub issues. The official site keeps a view of submissions from any agent and a "Bash Only" view, which it describes as "The default Verified view: every model in the same mini-SWE-agent environment". [38] The newest Verified entry in the site's data on 19 November 2026 was dated 26 February 2026, so these results are older than the releases in the comparison table.
| Agent | Model | % resolved | Entry date | Note |
|---|---|---|---|---|
| mini-swe-agent 2.0.0 | Claude 4.5 Opus (high) | 76.8 | 2026-02-17 | Bash Only view; the highest mini-swe-agent entry [38] |
| mini-swe-agent 2.0.0 | MiniMax M2.5 (high) | 75.8 | 2026-02-17 | Bash Only view; marked as an open-weights model; Gemini 3 Flash (high) has the same score [38] |
| OpenHands | GPT-5 | 71.8 | 2025-08-07 | Marked as performed or checked by the SWE-bench team [38] |
| OpenHands | Claude 4 Sonnet | 70.4 | 2025-05-24 | Marked as performed or checked by the SWE-bench team [38] |
| SWE-agent | Claude 4 Sonnet | 66.6 | 2025-05-22 | Marked as performed or checked by the SWE-bench team [38] |
The rows differ in model, harness version and date, so they do not compare the three agents with each other. The mini-swe-agent README separately claims more than 74% on SWE-bench Verified without naming the model. [12]
Running an open stack end to end
A reader who wants every layer to be inspectable needs an open-source agent, an open-weight model and a local inference server. In the documentation read for this article the agent reaches the server over HTTP, usually through an OpenAI-compatible API: opencode's documentation, for example, reaches Ollama, LM Studio and vLLM at /v1 endpoints, and Pi's documents the llama.cpp router server. [44][46] Setting up the server side is covered in how to run LLMs locally, self-hosting LLMs and local AI; model choices by memory size are in Best Local and On-Device LLMs and Best Open-Source LLMs.
Which agents document local models
| Tool | Local runtimes named in the documentation | Documented requirement or caveat |
|---|---|---|
| opencode | Ollama, LM Studio and vLLM with built-in discovery; any OpenAI-compatible endpoint as a custom provider | Only Ollama models whose metadata includes the completion capability are listed; discovered vLLM models start with tools disabled [44] |
| Codex CLI | ollama and lmstudio are built-in provider IDs; custom providers take a base URL | Provider settings must be in the user-level configuration file; project files cannot change them [41] |
| Pi | llama.cpp router server; custom providers | The router loads and unloads GGUF models on demand [46] |
| OpenHands | LM Studio, Ollama, vLLM, SGLang | "Local LLMs can have limited functionality"; a GPU-backed server is advised [45] |
| Cline | Ollama, LM Studio, Atomic Chat; any OpenAI-compatible API | Enable "Use Compact Prompt"; 16-32 GB of RAM for small quantized models, 32-64 GB for mid-size coding models, 64 GB or more for larger models and context windows [7][40] |
| goose | Ollama, LM Studio; OpenAI-compatible endpoints such as vLLM | "goose relies heavily on tool calling capabilities"; a model without function calling can only do chat completion, with all extensions disabled [42] |
| Aider | Ollama and other local servers | Ollama's default 2k context window is too small and silently discards excess context; the guide starts the server with an 8k window [39] |
| Qwen Code | Ollama, vLLM; OpenAI, Anthropic and Gemini protocols | None stated in the README [10] |
| Kilo Code | Ollama | Local models are more likely to loop or call tools incorrectly; the guide recommended qwen3-coder:30b when read [43] |
| mini-swe-agent | Any model through LiteLLM; a vLLM example for SWE-bench runs | Version 2 calls its bash tool through the model's native tool-calling interface by default; a text-based mode that parses commands from the reply remains for models without one [12][49][80] |
| Kimi Code CLI | Third-party services through the OpenAI-compatible protocol | Works out of the box with Moonshot's Kimi models [13][48] |
Gemini CLI is absent from this table because its README describes access only through Google licences and keys, and Mistral Vibe's README describes signing in with a Mistral account or API key. [5][14] Zed lists Ollama, LM Studio and OpenAI-compatible endpoints among the providers for its own agent. [47]
The caveats in the table come from the projects themselves, and they fall into three groups: context size (Aider), tool calling (goose), and the lower reliability of small local models (Kilo Code and OpenHands). [39][42][43][45] The Terminal-Bench 4.1 board gives a dated data point on open-weight models in agent harnesses. The best mini-swe-agent entry on 19 November 2026 was MiMo V2.6 Pro at 27.0%, while Kimi K3.1 Pro scored 59.7% ± 4.2 inside the proprietary Claude Code; this wiki lists both models as open-weight. [36] The two entries differ in both model and harness, so they do not isolate the effect of either.
Telemetry and data handling
An open-source licence does not mean an agent sends nothing home. The defaults below are as each project documents them; the table covers only projects whose documentation on this point was read for this article. Whatever the agent's own telemetry setting, prompts and code are still sent to whichever model provider is configured unless that provider is a local server.
| Tool | Documented default |
|---|---|
| Aider | Analytics are collected only after the user opts in; the docs say code, chat messages and keys are never collected [50] |
| Cline | Usage and error telemetry is on by default in the extensions, desktop app and CLI, and can be turned off in settings or with telemetryOptOut [51] |
| goose | Asks on first use for permission to collect anonymous usage data [52] |
| Pi | enableInstallTelemetry (anonymous install and update reporting) defaults to true; enableAnalytics defaults to false [53] |
| Gemini CLI | Collects usage statistics; the terms page says users may opt out of sending them to Google [54] |
| Mistral Vibe | Telemetry and crash reporting are turned off by setting enable_telemetry = false [14] |
| opencode | The Enterprise page of the V1 documentation says: "OpenCode does not store your code or context data. All processing happens locally or through direct API calls to your AI provider." The V2 documentation read for this article has no page on telemetry or data handling [55] |
| Zed | Collects anonymous telemetry; client-side metrics and crash reports can be disabled in settings [56] |
| Continue (final release) | The 2.0.0 release removed anonymous telemetry [23] |
Sandboxing and permission models
What an agent may do without asking differs from tool to tool.
| Tool | Documented model |
|---|---|
| Codex CLI | Commands run inside an operating-system sandbox by default: Seatbelt on macOS, bubblewrap on Linux and WSL2, a native sandbox on Windows. Sandbox modes include a read-only mode; approval policies include on-request and never [57] |
| Gemini CLI | Documents five sandboxing methods: macOS Seatbelt, Docker or Podman containers, a Windows native sandbox, gVisor and LXC/LXD (experimental) [58] |
| OpenHands | Can run without a sandbox (the README warns that the agent then has full access to the filesystem), in one Docker container, or with a separate container per conversation [6] |
| mini-swe-agent | Runs each action as an independent subprocess; supports local, Docker or Podman, Singularity or Apptainer, and bubblewrap environments [12] |
| Qwen Code | Built-in sandboxing and optional git worktrees for wide-ranging edits [10] |
| Cline | Every file edit and terminal command needs approval unless auto-approve is switched on [7] |
| opencode | Rules of allow, deny or ask per action and resource. The base policy allows every action and asks before reading .env files [60] |
| goose | "Autonomous Mode is applied by default"; a manual-approval mode and a risk-based approval mode can be selected [59] |
| Kilo Code | kilo run --auto approves permission prompts automatically unless a rule denies the action; the README says to use it only in trusted environments [11] |
| Pi | "Pi does not include a built-in permission system"; the project advises running it in a container, virtual machine or sandbox [4][61] |
| Zed | agent.tool_permissions with a global default and per-tool always_allow, always_deny and always_confirm patterns [62] |
Licence changes and governance events
A licence file describes the code as it stands today. Who maintains a project, and under what terms new versions appear, can change. The events below are from primary sources unless marked.
| Date | Event | Source |
|---|---|---|
| 2025-12-09 | The Linux Foundation announces the Agentic AI Foundation, with Block contributing goose alongside Anthropic's Model Context Protocol and OpenAI's AGENTS.md | [63] |
| 2026-02-22 | Kilo-Org/kilocode-legacy is created to hold Kilo's earlier extension under Apache-2.0; it is now archived, and its README says the legacy extensions reached end of life on 31 July 2026. The current Kilo-Org/kilocode repository is MIT, with copyright lines for Kilo Code and opencode | [11][64] |
| 2026-03-30 | Earendil's licensing RFC for Pi states that "Pi remains MIT licensed and that will not change", while future related parts may be Fair Source or proprietary | [68] |
| 2026-04-08 | Earendil Inc. announces its acquisition of the Pi project from its author, Mario Zechner | [67] |
| 2026-04-21 | Kilo's blog reports that Roo Code is shutting down and notes that "Kilo started as a fork of Roo" | [65] |
| 2026-04-28 | Warp opens the source of its client | [19] |
| 2026-05-15 | The Roo Code extension is shut down; the repository, since archived, publishes its last release (v3.54.0) the same day | [20][21] |
| 2026-06-18 | Free individual access to Gemini CLI ends; Google directs those users to Antigravity CLI, which is not open source | [5][34] |
| 2026-06-18 | The trade site Web Developer (a secondary source) gives this as the date on which Cursor announced that it had acquired Continue. Continue's own website says "Continue was acquired by Cursor" without giving a date. The final release tag, v2.0.0-vscode, was published on GitHub on 19 June 2026 (UTC), and the README calls the repository read-only | [23][24][79] |
| 2026-07-15 | Anaconda's blog announces the acquisition of Kilo Code, referring to Kilo's "open source and source-available codebase" | [66] |
Several lineages connect tools on this page. Roo Code began as a fork of Cline (its shutdown notice calls Cline the project "from where Roo Code originated"), and Kilo began as a fork of Roo. [21][65] Kilo's current CLI is, in its README's words, "a fork of OpenCode", meaning Anomaly's opencode. [11] Qwen Code was originally based on Gemini CLI. [10] Kimi Code CLI's README says its terminal interface is built on Pi's pi-tui library. [13] The archived Roo Code and Continue repositories remain available under Apache-2.0. [20][23]
Choosing by documented capability
These pointers restate facts from the tables above; they are not recommendations.
- Operating-system sandbox on by default: Codex CLI's documentation says commands run inside an OS-level sandbox by default. [57]
- Approval before every edit and command by default: Cline. [7]
- Editor integration: Cline (VS Code, with a closed JetBrains plugin) and Kilo Code (VS Code and JetBrains) ship editor extensions; Kimi Code CLI and other agents can be driven from Zed and other editors over the Agent Client Protocol. [7][11][13][78]
- Self-hosted web interface and automations: OpenHands. [6]
- Foundation governance, not a single vendor: goose, a project of the Agentic AI Foundation. [8][63]
- Local servers detected without manual configuration: opencode documents built-in discovery for Ollama, LM Studio and vLLM. [44]
- Bash as the only tool: mini-swe-agent. Version 2 calls it through the model's native tool-calling interface by default and keeps a text-based mode for models without one. [12][80]
- Analytics off unless the user opts in: Aider. [50]
- Small core by design: mini-swe-agent (its README describes an agent class of about 100 lines) and Pi (described by its maintainers as minimal). [4][12]
Known limits and security issues
Coding agents read untrusted text (source files, issue comments, web pages, tool output) and can run commands, which makes them a target for prompt injection. The OWASP Gen AI Security Project describes indirect prompt injection as occurring when a model accepts input from external sources such as websites or files whose content alters its behaviour. [69] A 2025 study by Liu and colleagues built a test framework, AIShellJack, with 314 attack payloads covering 70 MITRE ATT&CK techniques, ran it against GitHub Copilot and Cursor, and reported attack success rates as high as 84% for executing malicious commands. [70] Pi's security guide makes the same point about its own tool: files, comments, command output and model responses can steer the model, and reviewing the transcript does not create a security boundary. [61]
Open-source agents have also had conventional software vulnerabilities, published as GitHub security advisories. The table gives one advisory per project as an example. It is not a list of each project's most severe issue.
| Project | Advisory | Published | Summary | Affected and fixed versions |
|---|---|---|---|---|
| Cline | GHSA-9ppg-jx86-fqw7 | 2026-02-17 | A compromised npm token was used to publish cline@2.3.0 with a postinstall script that installed an unrelated package; a corrected 2.4.0 was published about eight hours later. The VS Code extension was not affected [71] | cline 2.3.0 on npm; fixed in 2.4.0 |
| opencode | CVE-2026-22812 | 2026-01-12 | Unauthenticated HTTP server allowed arbitrary command execution [72] | opencode-ai before 1.0.216 |
| Codex CLI | CVE-2025-59532 | 2025-09-19 | Sandbox bypass caused by a bug in path configuration logic [73] | @openai/codex 0.2.0 to 0.38.0; fixed in 0.39.0 |
| Zed | CVE-2026-27967 | 2026-02-25 | Symlink escape in the agent's file tools [74] | Before 0.225.9 |
| goose | CVE-2026-72718 | 2026-07-24 | Arbitrary command execution in goose review through a git core.fsmonitor setting [75] | Before 1.44.0 |
| OpenHands | CVE-2026-33718 | 2026-03-23 | Command injection in the git diff handler [76] | 1.4.0 and earlier; fixed in 1.5.0 |
| Pi | CVE-2026-54325 | 2026-06-08 | Project-local extensions were loaded without approval [77] | Before 0.79.0 |
On 19 November 2026 the repositories listed 12 published advisories for Zed, 4 for Pi, 3 each for Cline and opencode, and 1 each for Codex, goose and OpenHands; Cline, opencode and Zed each had one rated critical. [2][3][4][6][7][8][17] OpenHands's software-agent-sdk repository listed two more, both published on 13 November 2026, in which the OpenAI-compatible gateway let agent commands run outside the Docker sandbox in openhands-agent-server 1.49.0 to 1.60.2 (fixed in 1.61.0). [86]
Two of the entries in the table concern the safeguards themselves (a sandbox bypass in Codex CLI and a file-tool escape in Zed), and the Cline entry concerns the package registry through which the tool is distributed. The table is not a measure of which tool is less safe: Aider, Gemini CLI, Kilo Code, Qwen Code, mini-swe-agent, Kimi Code CLI and Mistral Vibe had no published advisories on GitHub on 19 November 2026, which does not show that they have had fewer flaws. [5][9][10][11][12][13][14] Among the mitigations the projects document, Pi's guide advises running the agent inside a container, virtual machine or sandbox and limiting the credentials and network services available to it, and Codex's documentation pairs its sandbox with an approval policy under which the agent asks before going beyond the sandbox boundary. [57][61]
Continue reading
- Best AI Coding AssistantsAs of 23 September 2026, the two tools at the top of the official Terminal-Bench 4.0 leaderboard are OpenAI's Codex and Anthropic's Claude Code.Listed in See also
- Best Open-Source LLMsAs of November 17, 2026, the highest-scoring open-weight large language model is Moonshot AI's Kimi K3.1 Pro, whose weights Moonshot released on November 4.Listed in See also
- Best Local and On-Device LLMsAs of November 2026, the best local LLM to run offline depends almost entirely on how much memory you can give it, so this guide ranks picks by hardware tier.Listed in See also
- Open-source licenseAn open-source license is a software license that complies with the Open Source Definition (OSD), a ten-point standard maintained by the Open Source Initiative (OSI).Listed in See also
- AI coding agentAn AI coding agent is an autonomous artificial intelligence system that can independently plan, write, test, debug, and deploy software code with minimal human oversight.Listed in See also
- Open-source AIOpen-source AI refers to artificial intelligence systems whose recipients have broad rights to use, study, modify, and share the system, together with access to the materials needed to exercise those rights.Listed in See also
More to read
- MIT License
- Open Source Initiative
- Apache License 2.0
- Coding agent
- opencode (SST)
- Cline (AI coding agent)
Topics:AI AgentsAI Code GenerationDeveloper ToolsOpen Source AI
References
- ^1 ^2 ^3 ^4 ^5Open Source Initiative. "OSI Approved Licenses". opensource.org, accessed 19 November 2026. opensource.org/licenses
- ^1 ^2 ^3 ^4anomalyco. "opencode" (repository, README, LICENSE and security advisories). GitHub, read 19 November 2026. github.com/...opencode
- ^1 ^2 ^3OpenAI. "codex" (repository, README, LICENSE and security advisories). GitHub, read 19 November 2026. github.com/...codex
- ^1 ^2 ^3 ^4 ^5 ^6earendil-works. "pi" (repository, README, LICENSE and security advisories). GitHub, read 19 November 2026. github.com/...pi
- ^1 ^2 ^3 ^4 ^5 ^6google-gemini. "gemini-cli" (repository, README and LICENSE). GitHub, read 19 November 2026. github.com/...gemini-cli
- ^1 ^2 ^3 ^4 ^5 ^6 ^7OpenHands. "OpenHands" (repository, README, LICENSE and security advisories). GitHub, read 19 November 2026. github.com/...OpenHands
- ^1 ^2 ^3 ^4 ^5 ^6 ^7 ^8 ^9cline. "cline" (repository, README, LICENSE and security advisories). GitHub, read 19 November 2026. github.com/...cline
- ^1 ^2 ^3 ^4 ^5aaif-goose. "goose" (repository, README, LICENSE and security advisories). GitHub, read 19 November 2026. github.com/...goose
- ^1 ^2 ^3 ^4Aider-AI. "aider" (repository, README and LICENSE.txt). GitHub, read 19 November 2026. github.com/...aider
- ^1 ^2 ^3 ^4 ^5 ^6QwenLM. "qwen-code" (repository, README and LICENSE). GitHub, read 19 November 2026. github.com/...qwen-code
- ^1 ^2 ^3 ^4 ^5 ^6 ^7 ^8Kilo-Org. "kilocode" (repository, README and LICENSE). GitHub, read 19 November 2026. github.com/...kilocode
- ^1 ^2 ^3 ^4 ^5 ^6 ^7 ^8SWE-agent. "mini-swe-agent" (repository, README and LICENSE.md). GitHub, read 19 November 2026. github.com/...mini-swe-agent
- ^1 ^2 ^3 ^4 ^5 ^6MoonshotAI. "kimi-code" (repository, README and LICENSE). GitHub, read 19 November 2026. github.com/...kimi-code
- ^1 ^2 ^3 ^4 ^5mistralai. "mistral-vibe" (repository, README and LICENSE). GitHub, read 19 November 2026. github.com/...mistral-vibe
- ^1 ^2Python Package Index. "aider-chat" (release history). pypi.org, read 19 November 2026. pypi.org/...aider-chat
- ^OpenHands. "software-agent-sdk" (repository and LICENSE). GitHub, read 19 November 2026. github.com/...software-agent-sdk
- ^1 ^2 ^3zed-industries. "zed" (repository, README, licence files and security advisories). GitHub, read 19 November 2026. github.com/...zed
- ^1 ^2warpdotdev. "warp" (repository, README and licence files). GitHub, read 19 November 2026. github.com/...warp
- ^1 ^2Zach Lloyd. "Warp is now open-source". Warp, 28 April 2026. warp.dev/...warp-is-now-open-source
- ^1 ^2 ^3RooCodeInc. "Roo-Code" (archived repository, README and LICENSE). GitHub, read 19 November 2026. github.com/...Roo-Code
- ^1 ^2 ^3Roo Code. "Roo Code Docs" (Extension Shutdown notice, last updated 15 May 2026). roocodeinc.github.io/Roo-Code
- ^Zoo-Code-Org. "Zoo-Code" (repository and LICENSE). GitHub, read 19 November 2026. github.com/...Zoo-Code
- ^1 ^2 ^3 ^4continuedev. "continue" (repository, README and LICENSE). GitHub, read 19 November 2026. github.com/...continue
- ^"Cursor Acquires Continue, Putting a Pioneering Open-Source Coding Agent Under Commercial Control". Web Developer, 18 June 2026. webdeveloper.com/...res-continue-open-source-agent
- ^SWE-agent. "SWE-agent" (repository, README and LICENSE). GitHub, read 19 November 2026. github.com/...SWE-agent
- ^plandex-ai. "plandex" (repository, README and LICENSE). GitHub, read 19 November 2026. github.com/...plandex
- ^voideditor. "void" (archived repository, README and LICENSE.txt). GitHub, read 19 November 2026. github.com/...void
- ^1 ^2opencode-ai. "opencode" (archived repository, README and LICENSE). GitHub, read 19 November 2026. github.com/...opencode
- ^MoonshotAI. "kimi-cli" (archived repository). GitHub, read 19 November 2026. github.com/...kimi-cli
- ^1 ^2charmbracelet. "crush" (repository, README and LICENSE.md). GitHub, read 19 November 2026. github.com/...crush
- ^"FSL - Functional Source License". fsl.software, accessed 19 November 2026. fsl.software
- ^Anthropic. "claude-code" LICENSE.md. GitHub, read 19 November 2026. github.com/...LICENSE.md
- ^GitHub. "copilot-cli" LICENSE.md (GitHub Copilot CLI License). GitHub, read 19 November 2026. github.com/...LICENSE.md
- ^1 ^2 ^3google-antigravity. "antigravity-cli" (repository and README). GitHub, read 19 November 2026. github.com/...antigravity-cli
- ^TabbyML. "tabby" LICENSE. GitHub, read 19 November 2026. github.com/...LICENSE
- ^1 ^2 ^3 ^4 ^5 ^6 ^7 ^8Terminal-Bench. "Terminal-Bench 4.1" leaderboard. tbench.ai, accessed 19 November 2026. tbench.ai
- ^Terminal-Bench. "Terminal-Bench 4.1". Terminal-Bench news, 9 November 2026. tbench.ai/...terminal-bench-4-1
- ^1 ^2 ^3 ^4 ^5 ^6 ^7SWE-bench. "SWE-bench Leaderboards". swebench.com, accessed 19 November 2026. swebench.com
- ^1 ^2Aider. "Ollama". Aider documentation, accessed 19 November 2026. aider.chat/...ollama
- ^Cline. "Local models". Cline documentation, accessed 19 November 2026. docs.cline.bot/...overview
- ^OpenAI. "Advanced Configuration". Codex documentation, accessed 19 November 2026. learn.chatgpt.com/...config-advanced
- ^1 ^2goose. "Configure LLM Provider" (Supported LLM Providers). goose documentation, accessed 19 November 2026. goose-docs.ai/...providers
- ^1 ^2Kilo Code. "Using Ollama with Kilo Code". Kilo documentation, accessed 19 November 2026. kilo.ai/...ollama
- ^1 ^2 ^3OpenCode. "Providers". OpenCode documentation, accessed 19 November 2026. opencode.ai/...providers
- ^1 ^2OpenHands. "Run Local LLMs with OpenHands". OpenHands Docs, accessed 19 November 2026. docs.openhands.dev/...local-llms
- ^1 ^2earendil-works. "Local Models with llama.cpp". Pi coding agent documentation, read 19 November 2026. github.com/...llama-cpp.md
- ^Zed Industries. "Use API Access". Zed documentation, accessed 19 November 2026. zed.dev/...use-api-access
- ^Moonshot AI. "Providers and models". Kimi Code CLI Docs, accessed 19 November 2026. moonshotai.github.io/...providers
- ^SWE-agent. "Local models". mini-SWE-agent documentation, accessed 19 November 2026. mini-swe-agent.com/...local_models
- ^1 ^2Aider. "Analytics". Aider documentation, accessed 19 November 2026. aider.chat/...analytics
- ^Cline. "Cline Telemetry". Cline documentation, accessed 19 November 2026. docs.cline.bot/...telemetry
- ^goose. "Anonymous Usage Data". goose documentation, accessed 19 November 2026. goose-docs.ai/...usage-data
- ^earendil-works. "Settings Reference" (Updates, telemetry, and warnings). Pi coding agent documentation, read 19 November 2026. github.com/...settings.md
- ^Google. "Gemini CLI: License, Terms of Service, and Privacy Notices" (last updated 10 April 2026). Gemini CLI documentation. geminicli.com/...tos-privacy
- ^OpenCode. "Enterprise". OpenCode V1 documentation (a previous version of the docs), accessed 19 November 2026. opencode.ai/...enterprise
- ^Zed Industries. "Telemetry in Zed". Zed documentation, accessed 19 November 2026. zed.dev/...telemetry
- ^1 ^2 ^3OpenAI. "Sandbox". Codex documentation, accessed 19 November 2026. learn.chatgpt.com/...sandboxing
- ^Google. "Sandboxing in Gemini CLI". Gemini CLI documentation, accessed 19 November 2026. geminicli.com/...sandbox
- ^goose. "goose Permission Modes". goose documentation, accessed 19 November 2026. goose-docs.ai/...goose-permissions
- ^OpenCode. "Permissions". OpenCode documentation, accessed 19 November 2026. opencode.ai/...permissions
- ^1 ^2 ^3earendil-works. "Run Pi safely". Pi coding agent documentation, read 19 November 2026. github.com/...security.md
- ^Zed Industries. "Tool Permissions". Zed documentation, accessed 19 November 2026. zed.dev/...tool-permissions
- ^1 ^2The Linux Foundation. "Linux Foundation Announces the Formation of the Agentic AI Foundation (AAIF), Anchored by New Project Contributions Including Model Context Protocol (MCP), goose and AGENTS.md". Press release, 9 December 2025. linuxfoundation.org/...f-the-agentic-ai-foundation
- ^Kilo-Org. "kilocode-legacy" (archived repository and README). GitHub, read 19 November 2026. github.com/...kilocode-legacy
- ^1 ^2Brian Turcotte. "Thank you, Roo! We'll take it from here." Kilo Blog, 21 April 2026. blog.kilo.ai/...thank-you-roo
- ^1 ^2David DeSanto and Scott Breitenother. "AI on Your Own Terms: Anaconda Acquires Kilo Code". Anaconda blog, 15 July 2026. anaconda.com/...anaconda-acquires-kilo-code
- ^Earendil Inc. "Announcing Pi & Lefos". earendil.com, 8 April 2026. earendil.com/...announcing-pi-and-lefos
- ^Armin Ronacher. "RFC 0015: Pi Licensing". rfc.earendil.com, 30 March 2026. rfc.earendil.com/...0015
- ^OWASP Gen AI Security Project. "LLM01:2025 Prompt Injection". genai.owasp.org, accessed 19 November 2026. genai.owasp.org/...llm01-prompt-injection
- ^Yue Liu, Yanjie Zhao, Yunbo Lyu, Ting Zhang, Haoyu Wang, David Lo. "'Your AI, My Shell': Demystifying Prompt Injection Attacks on Agentic AI Coding Editors". arXiv:2509.22040, submitted 26 September 2025, revised 28 April 2026. arxiv.org/...2509.22040
- ^Cline. "Unauthorized npm publish of Cline CLI cline@2.3.0 with modified postinstall script to install openclaw" (GHSA-9ppg-jx86-fqw7). GitHub Security Advisory, 17 February 2026. github.com/...GHSA-9ppg-jx86-fqw7
- ^anomalyco. "Unauthenticated HTTP Server Allows Arbitrary Command Execution" (GHSA-vxw4-wv6m-9hhh, CVE-2026-22812). GitHub Security Advisory, 12 January 2026. github.com/...GHSA-vxw4-wv6m-9hhh
- ^OpenAI. "Sandbox bypass due to bug in path configuration logic" (GHSA-w5fx-fh39-j5rw, CVE-2025-59532). GitHub Security Advisory, 19 September 2025. github.com/...GHSA-w5fx-fh39-j5rw
- ^Zed Industries. "Symlink Escape in Agent File Tools" (GHSA-786m-x2vc-5235, CVE-2026-27967). GitHub Security Advisory, 25 February 2026. github.com/...GHSA-786m-x2vc-5235
- ^goose. "Arbitrary command execution in goose CLI via `goose review` via git core.fsmonitor" (GHSA-r5pp-p5r8-466r, CVE-2026-72718). GitHub Security Advisory, 24 July 2026. github.com/...GHSA-r5pp-p5r8-466r
- ^OpenHands. "Command Injection in Git Diff Handler" (GHSA-7h8w-hj9j-8rjw, CVE-2026-33718). GitHub Security Advisory, 23 March 2026. github.com/...GHSA-7h8w-hj9j-8rjw
- ^earendil-works. "Pi loads project-local extensions without approval" (GHSA-mqxh-6gq7-558m, CVE-2026-54325). GitHub Security Advisory, 8 June 2026. github.com/...GHSA-mqxh-6gq7-558m
- ^1 ^2Zed Industries. "External Agents". Zed documentation, accessed 19 November 2026. zed.dev/...external-agents
- ^Continue. "Continue has joined Cursor" (notice on the project's home page). continue.dev, accessed 19 November 2026. continue.dev
- ^1 ^2SWE-agent. "v2.0 Migration Guide". mini-SWE-agent documentation, accessed 19 November 2026. mini-swe-agent.com/...v2_migration
- ^1 ^2Kilo-Org. "cloud" LICENSE.md (Open Core Ventures Source Available License version 1.0). GitHub, read 19 November 2026. github.com/...LICENSE.md
- ^1 ^2Kilo-Org. "kilo-desktop" LICENSE.md (Open Core Ventures Source Available License version 1.0). GitHub, read 19 November 2026. github.com/...LICENSE.md
- ^openinterpreter. "openinterpreter" (repository, README and LICENSE). GitHub, read 19 November 2026. github.com/...openinterpreter
- ^tailcallhq. "forgecode" (repository and LICENSE). GitHub, read 19 November 2026. github.com/...forgecode
- ^CodebuffAI. "freebuff" (repository, README and LICENSE). GitHub, read 19 November 2026. github.com/...freebuff
- ^OpenHands. "OpenAI-compatible gateway bypasses the Docker sandbox for new conversations, allowing agent commands to run on the host" (GHSA-h7m4-392w-vpjj). GitHub Security Advisory, 13 November 2026. github.com/...GHSA-h7m4-392w-vpjj
- ^TabbyML. "tabby" ee/LICENSE (The Tabby Enterprise license). GitHub, read 19 November 2026. github.com/...LICENSE
- ^anomalyco. "Figma skill materials" (NOTICE.md in the opencode repository). GitHub, read 19 November 2026. github.com/...NOTICE.md
Improve this article
Add missing citations, update stale details, or write a clearer explanation. Anyone can edit: changes go live when you publish, and every edit is checked by an editor.
1 revision · v1 · 6,739 words · full history
Fact-checks are independent of edits: a reviewer re-verifies the article against its sources and stamps the date. How we verify
Research and drafting on this wiki are AI-assisted, under named human editorial standards. How AI is used here
Reviewer note: Independent fact-check before publication on November 19, 2026: 345 claims checked against 131 cited and independent sources; 9 material and 15 minor corrections applied before publication.
Cite this page: AI Wiki. "Best Open-Source Coding Agents." aiwiki.ai, updated 19 Nov 2026, fact-checked 19 Nov 2026. CC BY 4.0. https://aiwiki.ai/wiki/best_open_source_coding_agents