agents-remember
Active·★ 29·MIT·Updated 2026-10-21
Agents Remember provides coding agents with durable, git-verified repository memory, ensuring project-specific rules are surfaced precisely when edits are made. It turns local invariants, naming rules, and other project facts into versioned Markdown files alongside the code, improving agents' ability to make safe and compliant changes.
#AI Agents#Coding Assistant#Git Integration#Context Management#Knowledge Base#Developer Tools#Memory Management
01
Features
01Path-addressed memory: Notes live at deterministic mirror paths, providing agents with relevant context without search or guesswork.
02Git-proven freshness: Memory (notes, overviews, catalogs) is drift-checked against source commits and scopes to ensure accuracy.
03Memory that lands with code: External memory repos use ledgers and dual worktrees to synchronize code and memory updates after approval.
04Repo-owned agent behavior: Each memory repo carries system files for path rules, tools, coding guidelines, and documentation sources.
02
Compatibility
Python 3.11+
Runtime
Verified via docs
Git
Dependency
Verified via docs
Docker
Optional Provider
Verified via docs
uv (uvx)
Installer
Verified via docs
03
Quick start
1
$ uvx agents-remember-mcp@latest --config /absolute/path/to/agents-remember-settings.json
04
Use cases
↳Ensuring coding agents adhere to project-specific rules and invariants when making changes deep within a codebase.
↳Providing agents with critical context like naming rules, migration scars, or 'looks safe but is not' facts at the point of edit.
↳Maintaining synchronized documentation and code, with memory updates landing only after approved code changes.
↳Bootstrapping new projects or onboarding agents with predefined path rules, tools, and coding guidelines.
05
Alternatives
mori★ 32
mori MCP server — A shared memory layer for AI coding agents — one that compounds.
fava-trails★ 26
🫛👣 FAVA Trails — Git-native, curated memory for AI agents via MCP. Draft isolation, promotion gate, thought lifecycle hooks, memory curation protocols, supersession chains.
infimium-agent★ 25
Infimium helps agents find the right code, docs, and dependencies — before they edit. Local-first, open-source, MCP-compatible.
okf-agent-memory★ 827
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
mcp-local-memory★ 60
A lightweight, powerful local memory server for AI agents supporting text, entities, and relations. Enables persistent codebase understanding and user preference management.
Comments
Log in to leave a comment
No comments yet. Be the first!