#agent-memory

Build your HUMAN.md.

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

🔁 Build reliable recurring AI-agent systems: 968 resources, 22 operational patterns, 22 loop contracts, 8 runtime starters, an interactive atlas, and a structured dataset.

Live context engine for AI agents: resolve verified workspace state before the context window opens. Pairs with Perseus Vault for persistent encrypted memory. Local-first, MIT. pip install perseus-ctx

The #1 Obsidian MCP for AI memory — freshness-aware, cited, local-first and read-only by default. Dataview, Bases, PDFs, every agent.

Any brain, any agent. Package an AI agent's brain — persona, MCP stack, skills, memory, config — into one open, signed bundle and install it into any framework (OpenClaw, Hermes, Claude Code) in one click.

Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agent-native, Obsidian-compatible second brain — markdown RAG, no vector DB.

Turns working with Claude Code into a system that finishes goals: what you teach, verify, and solve once stays in use — session after session.

Async hierarchical memory middleware for LLM agents.

Multi-agent memory substrate for PostgreSQL — provenance-gated, vector-hybrid recall

AccInt - local-first MCP Work Model for coding agents that learns from real outcomes.

A shared knowledge vault + full software-engineering workflow for AI coding agents — run Claude Code and Codex in parallel with one memory, one plan.

Long-term memory for AI agents that stays correct — zero-dependency Python + MCP server for Claude Code. When a fact is corrected, the old value stops coming back.

Cross-platform kit that gives AI agents (Claude Code, Codex, Cursor) persistent memory: Markdown vault + git + MCP. Local-first, hybrid search optional.

Personal markdown memory for coding agents — brain-modelled curator, three retrieval tiers, lives on your disk.

AI agent knowledge & long-term memory · MCP server, knowledge graph, BM25 + RRF retrieval · drop-in for Claude Code/ Openclaw/ Cursor / Codex / Hermes

Local-first MCP server for shared memory, reservations, handoffs, and review evidence across AI coding agents.

Local-first memory engine for AI-agent teams — private/team/project ACL, associative recall, federated sync, and a built-in MCP server. One SQLite file, no LLM required. Apache-2.0.

MCP-native knowledge-graph memory for AI agents

Local-first control plane for AI-agent teams — orchestrates Claude Code, Codex, Grok, agy & Hermes into gated workflows that fix their own failures, with per-run metering, an append-only audit log, and team memory. Apache-2.0.

The continuity substrate for AI agents — memory that becomes a mind: a versioned self-model, a cognitive heartbeat, a shared cortex, metacognition & debate, on temporal-graph memory. Apache-2.0, zero-dep core.

Claude Code hook that blocks fixes that already failed - fingerprints edits, links them to test outcomes, survives context compaction. 100% of disguised repeat fixes caught, zero false blocks (npm run bench).

Local memory, context, and trust-boundary layer for cloud LLM coding agents

One config for every AI coding agent — cross-tool config + a cognitive substrate (memory, blast-radius, guardrails) for Claude Code, Codex, Cursor, Gemini, Aider, and more.

Multi-Agent AI research platform using LangGraph for automated AI research. Orchestrate specialized agents (Planner, Researcher, Writer, Human-in-the-loop). Features a FastAPI backend, parallel web/academic retrieval (Tavily/Arxiv), and a React frontend for generating cited, grounded AI answer.

A control-theoretic learning plane for Hermes-style AI agents

Catch visible-but-unbound coding-agent handoffs: CLI + GitHub Action with proof, policy gates, SARIF, HTML, and benchmark cards.

Universal control system for coding agents: shared memory, cross-project handoffs, research management, & MCP + Obsidian dashboards across products/repos.

OpenCode memory governance plugin — Knowledge Graph + Hybrid Search + Smart Compaction + Tool Firewall + Stop Gate. 6 MCP tools with slash-command UX. Apache-2.0.

HermesClaw Zero‑Config Sidecar is a lightweight local vector‑memory engine for Hermes and OpenClaw. It runs as a zero‑config sidecar, providing fast embeddings, persistent memory, and instant retrieval for agents and MCP tools. Built for speed, simplicity, and full local control.

agent wayfinding. temporal knowledge store in one sqlite file. no neo4j, no cloud, no lock-in.

CNAA provides a lightweight cloud backend that allows AI agents to maintain persistent state across devices through MCP. Unlike traditional memory systems, CNAA does not perform reasoning or prompt engineering. It simply stores and serves structured agent state.

Governed operating loops and portable capability Capsules for persistent AI agents

Local-first AI agent memory for coding projects: SQLite context, MCP server, Codex skill, Rust CLI, and optional embeddings.

A cloud of trusted and proven memories for your AI agents.

Self-hosted memory for Claude — markdown knowledge base with wikilink graph, hybrid semantic search (pgvector + Ollama), and a first-party MCP server. One docker compose up.

Agent Memory Kit System: Capture every correction and interaction to build your own SLM from day one

Local-first research memory for humans and AI agents. Turn saved links, notes, and web sources into a private Markdown source library.

🌐 EN/PT/ES/中文 · Hierarchical L0-L3 memory layer for AI agents — second brain with Web UI (4 languages), multimodal RAG, notes, and skill generation. Add-on for Mnemosyne. Windows/macOS/Linux/Raspberry Pi.

AI-agent reliability and governance layer: auto-firing compliance checks, persistent memory, security scanning, and verification loops that wrap any AI agent.