A local-first memory tool for Gemini CLI and other AI agents, keeping remembered information grounded in its original sources. Gemini CLI is a command-line program for using Gemini from a terminal.

Use it to give AI agents persistent, locally stored, source-based memory.

It helps an agent retain useful project information between interactions without relying only on the current conversation. Source grounding makes it possible to trace memories back to supporting material.

talamus — Plugin for Gemini CLI by ampres-ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/ampres-ai/talamus

Made for: Gemini CLI.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/ampres-ai/talamus/gemini-extension.svg)](https://agentmods.dev/plugins/ampres-ai/talamus/gemini-extension)

Your own site

<a href="https://agentmods.dev/plugins/ampres-ai/talamus/gemini-extension"><img src="https://agentmods.dev/badge/plugins/ampres-ai/talamus/gemini-extension.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

talamus scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

gemini-extension.json · 18 lines

What it actually says

{
  "name": "talamus",
  "version": "1.1.3",
  "description": "Local-first, source-grounded memory for Gemini CLI and other AI agents.",
  "mcpServers": {
    "talamus": {
      "command": "uvx",
      "args": [
        "--with",
        "mcp>=1.29,<3",
        "talamus==1.1.3",
        "mcp",
        "serve"
      ]
    }
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today First seen · 18 lines scan A c59c518aba93

Subscribe to this mod's changes

talamus is a plugin published in the GitHub repository ampres-ai/talamus (3 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.

Memory and context agent-memory ai-agents knowledge-graph local-first mcp second-brain

engraphis-memory

Give agents durable, scoped, explainable memory across sessions and repos via the Engraphis MCP tools. Use when you learn something worth keeping, need prior context before acting, or ask why/how a fact changed. Covers remember/recall, why/timeline, forget/pin/correct, sessions, and code search.

Coding-Dev-Tools/engraphis · not measured

superlocalmemory-codex

Local-first agent memory with auditable hybrid retrieval — the Codex build, with Codex-shaped rules, hooks and launcher.

qualixar/superlocalmemory · not measured

agentmemory

Upstream-compatible AgentMemory plugin bundled with the independent Windows/Codex downstream. 12 hooks, 56 MCP tools, 8 skills, real-time viewer.

M-T-D-N/agentmemory-codex-windows · not measured

autograph

Schema-as-code memory engine for Obsidian vaults that AI agents write to: typed cards, entity dedup, link repair, update-in-place (supersede + History), Ebbinghaus decay, MOC generation, and a vault health score. Plain Markdown you own, Python stdlib only. Ships the autograph skill plus a /research slash command that…

smixs/autograph · not measured

journal

Personal journaling system built on Binder — morning briefings, day planning, reflections, summaries, and period-level goal tracking.

mpazik/Binder · not measured

tree-ring-memory

Local-first memory lifecycle, project bootstrap, and receipt-backed harness guidance for Claude Code using Tree Ring Memory v0.15+.

TerminallyLazy/Tree-Ring-Memory · not measured