# Living Brain

> Source: https://aiwiki.ai/wiki/living_brain
> Updated: 2026-11-05
> Categories: AI Agents, AI Tools & Products, Developer Tools
> License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) - attribute to "AI Wiki (aiwiki.ai)"
> Cite as: AI Wiki. "Living Brain." aiwiki.ai, 5 Nov 2026. https://aiwiki.ai/wiki/living_brain
> From AI Wiki (https://aiwiki.ai), the free encyclopedia of artificial intelligence. Reuse freely with attribution.

**Living Brain** is a hosted [agent memory](https://aiwiki.ai/wiki/agent_memory) service from ChatAndBuild. It stores information outside a [large language model](https://aiwiki.ai/wiki/large_language_model), organizes it into connected knowledge pages, and makes selected material available to assistants and custom agents across sessions. Its developer platform provides an API, SDKs, a command-line interface and [Model Context Protocol](https://aiwiki.ai/wiki/model_context_protocol) (MCP) integrations. The API documentation identifies the service as being in early access.[1][2]

## Overview

Living Brain separates stored knowledge from the model that answers a question. A user can accumulate notes, documents and conversations in a brain, then let a connected assistant retrieve that material. The documentation describes a brain as a knowledge store belonging to an end-user subject, with each capture, compiled page and connection assigned to one brain.[3]

| Component | Documented purpose |
| --- | --- |
| Capture | Submitted material, such as a note, URL, file, transcript or chat turn |
| Ingest source | Record of a capture moving through background processing |
| Page | Maintained knowledge with a title, summary, body, version history and source links |
| Connection | Relationship between two pages, with a strength category and explanation |
| Brain profile | Instructions about vocabulary, priorities and how incoming material should be handled |

The product's compiled pages and connections form a [knowledge graph](https://aiwiki.ai/wiki/knowledge_graph). Its memory is supplied to a model at inference time. Retaining a new fact in these pages does not itself change that model's weights.[1][3]

## Capturing and maintaining knowledge

Capture processing is asynchronous. An initial request returns an ingest-source record; background processing extracts information, chooses an existing page or creates a page, records a version with source provenance, and refreshes retrieval data and connections. A source can report a failure even after a page has been saved if a later processing step fails.[3]

The capture interface accepts batches, with each item processed independently. A separate chat-turn operation uses a classifier to decide what should be retained from a conversation. Failed sources can be retried. Deleting an ingest source does not automatically delete pages already derived from it.[4]

Pages can be active, stale, contested, deprecated or archived. The documentation describes marking conflicting material as contested and preserving the competing claims for resolution. Brain-profile changes affect subsequent captures rather than retroactively recompiling existing pages.[3]

### Memory policies

Living Brain documents four internal policies for deciding how to maintain and reuse information.[5]

| Policy | Decision |
| --- | --- |
| Memory Worthiness Score (MWS) | Whether an extracted fact merits maintenance in a page |
| Placement Fit Score (PFS) | Which candidate page should receive a fact |
| Connection Resonance Score (CRS) | Whether a relationship between pages is useful |
| Re-entry Priority Score (RPS) | When a page should be resurfaced for a task |

The published policy descriptions include eligibility and permission checks before ranking. Their numerical weights and thresholds are not published, and the API does not return the policy scores. These scores express maintenance or retrieval decisions rather than probabilities that information is true. The documentation also distinguishes resurfacing relevant material from granting an agent permission to act.[5]

## Retrieval and prompt context

Living Brain combines semantic search with keyword matching. Semantic retrieval can find differently worded material, while keywords help preserve matches for names and identifiers. Search results indicate whether a match was semantic, keyword-based or both.[6]

The documented defaults return five results and apply a semantic-similarity floor of 0.35; keyword matches can remain below that floor. Search embeddings cover the title, summary and beginning of a page's body. A result's similarity field is a vector score, not a probability that the page answers the question, and it is separate from the combined ranking.[6]

For general session context, a prompt-index operation returns a compact selection of important pages, with pinned pages placed first. An agent can use this index at the beginning of a conversation and search for narrower evidence when needed. The graph API returns nodes and edges for an application to render; the sign-in MCP connector also provides an interactive graph inside compatible chat clients.[7]

This is a form of external memory retrieval related to [retrieval-augmented generation](https://aiwiki.ai/wiki/retrieval_augmented_generation). The maintained pages add a compilation stage before a later query, rather than requiring the answering model to assemble all related raw passages for each question.[3][7]

## Developer interfaces

| Interface | Documented implementation |
| --- | --- |
| TypeScript SDK | `@living-brain/sdk`; typed clients for runtimes with global `fetch`, including Node.js 18 or later[10] |
| Python SDK | `livingbrain-sdk`; synchronous and asynchronous clients, Pydantic v2 models, Python 3.10 or later[11] |
| CLI | `@living-brain/cli`; commands organized by API namespace, with structured output and a request-preview mode[12] |
| API-key MCP | Streamable HTTP server at `https://livingbrain.fernmcp.dev/livingbrain`[9] |
| Sign-in MCP | OAuth connection at `https://api.livingbrain.com/mcp`[13] |

The API-key MCP documentation includes integrations for [Claude Code](https://aiwiki.ai/wiki/claude_code), [OpenAI Codex](https://aiwiki.ai/wiki/openai_codex), [Cursor](https://aiwiki.ai/wiki/cursor) and Visual Studio Code. It maps API operations to tools for captures, brains, workspace content, integrations and webhooks. The sign-in connector is a separate route for compatible clients, including ChatGPT and Claude; the tools exposed depend on the OAuth scopes granted.[9][13]

API requests use an organization-scoped key and an `x-subject-id` identifying the end user. The key inherits the issuing member's role. The authentication guide instructs developers to keep organization keys on the server and use a backend proxy for browser access.[8]

### Imports and synchronization

The documentation provides a Markdown-vault importer and workflows for bringing in Claude-project material or a manually reviewed export of an assistant's remembered information. These workflows submit captures for compilation; connecting the service does not automatically copy every conversation or every memory from all other assistants.[14]

The importer uses source identifiers to avoid resubmitting unchanged notes. Deleting or renaming an original vault file does not remove previously compiled knowledge. Its documented text workflow also leaves binary attachments behind unless they are captured separately.[14]

Applications can follow a change feed or subscribe to webhooks for page changes, new connections, completed briefs and import progress. Daily briefs can run on a schedule or be requested directly. Acknowledging a change marks it as seen by a user; machine synchronization separately tracks its position in the feed.[15]

## Reported benchmark results

Living Brain publishes internal results on conversational-memory benchmarks. As inspected on November 5, 2026, its homepage and developer benchmark page reported different LoCoMo figures. The dated documentation run and the homepage figures should be treated as separate reports.[1][16]

| Measure | Documentation run, October 26, 2026 | Homepage report inspected November 5, 2026 |
| --- | --- | --- |
| Judged answer accuracy | 90.5%, or 1,393 of 1,540 questions | 92.2% over 1,540 questions |
| Memory context per question | About 6.8K tokens | About 9.4K tokens |
| Full-history context reference | About 26K tokens | About 26K tokens |
| Median retrieval time | 467 ms | 464 ms |
| Median total answer time | 9.8 seconds | 3.7 seconds |
| Answering model | GPT-5 | Not specified alongside the homepage result |

The documentation identifies the October 26 run as batch `4fd3f746`, with binary judgments against reference answers. Its full-history figure is a context-size comparison, without a reported accuracy result for that baseline. It also describes the figures as coming from one run.[16]

Separately, the homepage reports 22.6 times fewer tokens and 95% lower cost per task on LongMemEval-S against a 116K-token full-context baseline. It reports zero observed hallucinations under that evaluation's scoring criteria. Those observations do not establish that the service never produces false information.[1]

### Interpreting the evaluations

The original LoCoMo research evaluates long conversational histories through question answering, event summarization and multimodal dialogue generation. Its published question-answering results use an F1 metric. Living Brain's binary judged accuracy should therefore not be treated as directly interchangeable with the original paper's F1 scores.[16][17]

LongMemEval is a separate research benchmark covering information extraction, reasoning across sessions, temporal reasoning, knowledge updates and abstention. Its existence and design do not independently validate Living Brain's reported implementation results.[18]

The Living Brain benchmark documentation explicitly limits its LoCoMo evaluation to answering questions over a fixed history. It does not measure whether the service proactively resurfaces information at the right moment or whether people find its compiled pages useful. Internal rankings apply to the tested systems and configurations.[1][16]

## Related topics

- [Agent memory](https://aiwiki.ai/wiki/agent_memory)
- [Knowledge graph](https://aiwiki.ai/wiki/knowledge_graph)
- [Model Context Protocol](https://aiwiki.ai/wiki/model_context_protocol)
- [Retrieval-augmented generation](https://aiwiki.ai/wiki/retrieval_augmented_generation)

## References

1. Living Brain. [Official product website](https://livingbrain.com/). Product description, FAQ and internal benchmark statements; accessed November 5, 2026.
2. Living Brain. [Developer documentation overview](https://docs.livingbrain.com/). Early-access status and integration overview; accessed November 5, 2026.
3. Living Brain. [How a brain works](https://docs.livingbrain.com/docs/concepts). Capture pipeline, page lifecycle and knowledge connections; accessed November 5, 2026.
4. Living Brain. [Capturing knowledge](https://docs.livingbrain.com/docs/capturing). Capture operations and ingestion behavior; accessed November 5, 2026.
5. Living Brain. [Design policies](https://docs.livingbrain.com/docs/design-policies). Memory maintenance and resurfacing policies; accessed November 5, 2026.
6. Living Brain. [How search ranks pages](https://docs.livingbrain.com/docs/search-ranking). Search ranking and score interpretation; accessed November 5, 2026.
7. Living Brain. [Search and prompt context](https://docs.livingbrain.com/docs/search). Retrieval, prompt index and graph interfaces; accessed November 5, 2026.
8. Living Brain. [Authentication](https://docs.livingbrain.com/docs/authentication). Organization keys, subject identity and roles; accessed November 5, 2026.
9. Living Brain. [MCP with API key](https://docs.livingbrain.com/mcp). Hosted MCP transport and tools; accessed November 5, 2026.
10. Living Brain. [TypeScript SDK](https://docs.livingbrain.com/sdk/typescript). Package and runtime requirements; accessed November 5, 2026.
11. Living Brain. [Python SDK](https://docs.livingbrain.com/sdk/python). Package, clients and runtime requirements; accessed November 5, 2026.
12. Living Brain. [CLI](https://docs.livingbrain.com/cli). Command interface and output formats; accessed November 5, 2026.
13. Living Brain. [MCP with sign-in](https://docs.livingbrain.com/mcp/sign-in). OAuth connector and scope-dependent tools; accessed November 5, 2026.
14. Living Brain. [Importing existing knowledge](https://docs.livingbrain.com/docs/importing). Vault, assistant-memory and project imports; accessed November 5, 2026.
15. Living Brain. [Change feed and webhooks](https://docs.livingbrain.com/docs/changes). Synchronization and daily briefs; accessed November 5, 2026.
16. Living Brain. [Benchmarks](https://docs.livingbrain.com/docs/benchmarks). LoCoMo batch `4fd3f746`, October 26, 2026; accessed November 5, 2026.
17. Maharana, Adyasha, et al. [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://snap-research.github.io/locomo/). LoCoMo research project, 2024.
18. Wu, Di, et al. [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://arxiv.org/abs/2410.10813). arXiv:2410.10813, October 14, 2024; ICLR 2025.