Talamus
About
Local-first, source-grounded memory for AI agents, with durable Markdown, citations, bitemporal history, and review-gated corrections over MCP.
Details
- Author
- ampres-ai
- Categories
- AI
Jump to
Setup
Install Talamus in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/ampres-ai/talamus
Follow the installation instructions in the repository README, then restart your MCP client.
Your coding agent forgets why a decision was made as soon as the session ends.
Talamus keeps the decisions, evidence, and corrections worth remembering as ordinary Markdown, then gives Claude Code, Codex, Cursor, Gemini CLI, and any MCP agent cited recall in the next session.
No hosted account. No telemetry. No required embeddings. Plain search stays on your machine; LLM-backed actions use only the engine you choose.
Try the whole local retrieval loop first — no persistent install, account, LLM, or hook, and no files written outside./talamus-demo:
uvx --from talamus talamus demo --root ./talamus-demo uvx --from talamus talamus search "embedding" --root ./talamus-demo uvx --from talamus talamus read "Embedding" --root ./talamus-demo
If local, inspectable agent memory is useful to you,star Talamus on GitHub— it helps other builders discover a local-first alternative.
Talamus is an open-source project byAmpres, an independent AI and open-source lab.
Copy-pasteable arc, with the reproducible version inscripts/demo/run_magic.py:
-
Set up the project brain.talamus setupinitializes the brain, chooses an engine, installs MCP for Claude Code, Cursor, Codex, OpenCode, and OpenClaw when detected, asks once before installing the session-capture hook, and can probe the engine with one tiny live call.
Your agent session ends. The consented hook reads the transcript and git diff, applies the worth-remembering gate, writes only useful memory into this brain, and audits the event at.talamus/logs/capture.log.
A fresh session asks what happened and gets an answer from real notes, with sources.
talamus recall "why did we choose FTS5?" talamus ask "why did we choose FTS5?"
Reproduce the scripted demo without spending LLM calls, or run it with your real engine.
python scripts/demo/run_magic.py --fake python scripts/demo/run_magic.py --keep --engine claude-cli
TIME: notes have version history, facts have valid-time windows, andtalamus ask --as-of 2026-01answers from the brain as it was.
MEANING: the ontology is induced from evidence, versioned, promoted by measured rules, and used to cluster and route the brain.
VERIFIABILITY: every note carries provenance;talamus verifyproposes corrections to review, and answers cite the notes they used.
The one-screen benchmark is rendered in thebenchmark guideand committed asone-screen.md. Every number below traces to acommitted result artifact.
Also measured in committed artifacts:−97.7% tokensper answer versus loading the brain into context, refusal1.000on out-of-scope questions, and search latency p9572.6 msat 10k notes / p50624 msat 100k.
The honest part: retrieval quality tracks the LLM you bring. With a strong expansion engine,talamus-smartleads a strong multilingual dense model (multilingual-e5) on every metric including ranking (nDCG 0.847 vs 0.837); with a weak or free one, e5 leads ranking while Talamus keeps the best hit/recall — and on a slow local engine, plainsearchbeats--smartoutright. Every number traces to a committed artifact; the losses stay on the table.
Bring the LLM you already have:claude-cli,codex-cli,antigravity-cli(agy),opencode,ollama, oranthropic-api.
pipx install "talamus[mcp]" talamus setup talamus ingest ./notes && talamus ask "what should I remember?"
Runtalamusfor the status dashboard,talamus quickstartfor essential commands, ortalamus uifor the local React workbench.
Install the consent-aware Talamus agent skill fromskills.sh:
npx skills add ampres-ai/talamus --skill talamus-memory
OpenClaw can install the same standalone skill directly from ClawHub:
openclaw skills install @ampres-ai/talamus-memory
Installing the standalone skill does not install Talamus automatically. If the CLI is missing, the skill explains the isolated installation choices and asks before running one.
Gemini CLI can install Talamus directly from its extension gallery or from this repository. The extension starts the pinned PyPI release throughuvx, so it does not modify the cloned source tree:
gemini extensions install https://github.com/ampres-ai/talamus --auto-update
goose can install the repository as an Open Plugin. This adds the consent-aware memory skill and starts the pinned local MCP server for each new CLI session:
goose plugin install https://github.com/ampres-ai/talamus.git
The plugin requiresuvonPATH;uvxdownloads Talamus and its MCP dependencies into an isolated cache on first use.
Containerized MCP (the brain remains in the mounted local folder):
docker run --rm -i -v "$PWD:/data" ghcr.io/ampres-ai/talamus:1.1.1
Docs:quickstart,local-first agent memory,agent install guide,commands,agent tool calling,configuration,benchmarks,architecture,design principles,evaluation,multi-brain,ontology.
Project:security,contributing,roadmap,changelog.
Maintained byAmpres. Source code and issue tracking live atampres-ai/talamus.
pip install -e ".[dev,mcp]" python dev.py
python dev.pyruns ruff, format check, mypy, and unittest. Product behavior changes should update user docs in the same change.
Local-first agent memory: a plain-Markdown Obsidian vault is the source of truth, with a rebuildable DuckDB index for hybrid BM25 + vector + graph recall.
Persistent memory and semantic search for AI coding assistants across sessions
Give your agent a memory: shared, cited, tenant-isolated knowledge-graph memory for any MCP host. Grounded answers from a local-first June endpoint — abstains rather than guesses.
Decentralized persistent memory for AI agents — encrypted vault storage built on Walrus and Sui.
Persistent memory for AI assistants and coding agents across ChatGPT, Claude, Cursor, and other MCP-compatible tools.
Your portable AI memory vault — memories, skills & configs, shared across every AI tool.
Local Work Model for AI agents that learns from real outcomes.
Adaptive MCP memory system for AI applications. Learns which retrieval strategies work for your data, scores results using cognitive science models, builds a knowledge graph automatically, and validates every parameter change against real query history before adopting it. Patent pending.
Auditable, self-improving knowledge & memory for AI agents over MCP — citation-enforced answers and a replayable why-trace, self-hosted on Postgres.
Turns your task manager into agent memory: hybrid (RRF) retrieval over TickTick or an Obsidian vault via an adapter contract. MCP server + CLI, no vector DB to maintain.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
