MCP.Market

Talamus MCP server

by ampres-ai·io.github.ampres-ai/talamus·v1.1.3·3 stars
No reviews yet

Local-first, source-grounded memory that survives AI agent sessions.

A91/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A91/100

full report

Adoption
Growing

3 stars46 downloads/wk

Reviews

Write one

Nobody has reviewed Talamus yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Talamus tools (16)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • ask

    Ask the brain and get a written answer WITH CITATIONS to the exact notes used. Spends LLM calls on the user's configured engine (cheap tier for the routing, strong tier for the answer). Prefer `recall` when you only need raw context to reason over yourself — it costs zero LLM calls.

  • history

    The past versions of a brain note (transaction time), oldest first: when Talamus changed that record and how.

  • ingest_text

    Compile a text into brain notes (without the 'worth remembering' gate: use it for already-selected content). scope: 'project' (default) or 'central'.

  • neighbors

    Show concepts connected to a concept in the brain, with relation types.

  • ontology_status

    The state of the emergent type system: schema version, active/candidate types, and the coverage of typed edges.

  • overview

    Show the Talamus brain's domain map (name, description, note count): an overview to get oriented before searching. Read-only, no LLM cost.

  • propose_note

    Propose UNCERTAIN knowledge: it lands in the brain's review queue, not directly in the notes (F10.4). A human will apply or reject it.

  • read_note

    Read the full Markdown content of a Talamus note given its title.

  • recall

    Recall from the Talamus brain the context relevant to a question (real notes). Reason over the context yourself to answer.

  • remember

    Save into the Talamus brain an important insight or decision that emerged in the session, turning it into a note. scope: 'project' (default) or 'central' for the personal brain — writing to the global brain must be explicit.

  • review_apply

    Apply an item from the review queue (corrections are written to the brain while preserving history).

  • review_list

    The decisions pending in the brain's review queue.

  • review_reject

    Reject an item from the review queue (the decision stays recorded).

  • search

    Search the Talamus brain for notes relevant to a query; returns titles and summaries.

  • sources

    The sources (provenance) of a note: where each statement comes from.

  • verify

    Check whether a note is still faithful to its ORIGINAL source (Talamus preserves the source of every note). Returns ok, a proposed correction, or unchecked when the source is unavailable. Costs one LLM call when the source exists — use it before relying on a note that smells stale.

Public scan report

scanner v0.1.10 · 2026-10-31 · same rubric, same numbers if you re-run it

no findings
  • Code scan94 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 3 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 91/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Talamus compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
91/100
higher than 88% of 4,460 AI and agents servers
Tools
16
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
3
more than 75% of 2,711 AI and agents servers
Downloads a week
46
more than 38% of 1,538 AI and agents servers with a package

What its tools let an agent do: 16 read

Install Talamus in Claude Code, Cursor or VS Code

claude mcp add talamus -- uvx talamus
Add to Cursor

What the publisher says

From the Talamus repository's README, as published. We do not edit it. Read it on GitHub

Talamus

<!-- mcp-name: io.github.ampres-ai/talamus -->

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

For a technical evaluation, read the architecture and the measured benchmarks.

Talamus was created and is maintained by Giovanni “Angio” Crapuzzi under Ampres, an independent AI and open-source project. The engineering case study documents the architecture, measurements, and trade-offs behind the project.

Connect an agent

Copy-pasteable arc, with the reproducible version in scripts/demo/run_magic.py:

  1. Set up the project brain. talamus setup initializes 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.
talamus setup
  1. 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.
  1. 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?"
  1. 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

What is different

TIME: notes have version history, facts have valid-time windows, and talamus ask --as-of 2026-01 answers 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 verify proposes corrections to review, and answers cite the notes they used.

Measured comparison

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Talamus: common questions

Is Talamus MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the Talamus safety report
How do I install Talamus?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Talamus need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Talamus maintained?
The last commit was 7 days ago (2026-10-28). The latest release is v1.1.3.
What can I use instead of Talamus?
Servers from other publishers that do the same job: Basic Memory MCP server, Agent Recall MCP server and HOL Guard MCP server.
How does Talamus compare with other AI and agents MCP servers?
safety score 91/100 (higher than 88% of 4,460 AI and agents servers); tools 16 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Talamus

Same job from other publishers: the closest match first, then the best rated.

  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • Agent Recall
    Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.
    A
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Agent-Native Chat
    Minimal chat-first app with durable threads, actions, and the app-agent loop
    A
  • IWE (iwe.md)
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A