#agent-memory

The agentic harness for AI coding agents — intelligence is rented, the harness is owned. Runs the full work cycle: intent briefs, bounded RAG context from real code intelligence, persistent memory, preventive guardrails, and performance evals. One CLI + MCP server, SQLite inside. Claude Code, Codex, Gemini CLI, Cursor & OpenCode.

One reliable canonical source for AI coding agent rules, commands, skills, MCP, hooks, and permissions — synced across AI coding assistants.

MCP server with 40 tools for AI agents. Memory, web fetch, search, file ops, screenshots, and multi-agent coordination in one Go binary.

Memory security for AI agents. Scan native memory writes, gate tools on bound hosts, inspect what was stored. Not a second brain.

Self-hosted runtime for AI agents and workflows. Durable execution, capability-gated tools, human approval gates, and a memory system that accumulates. Runs survive restarts and resume where they stopped. Mount your domain logic as a plugin package or drive it over the HTTP SDK

Memory for AI agents that only remembers the latest truth: a bi-temporal belief ledger + transcript index in one SQLite file.

Local-first operating memory for AI coding agents - Claude Code, Codex, and any MCP client. Tracks decisions and their evolution. SQLite + on-device embeddings, no cloud.

Convert sessions across harnesses to a unified trajectory format - designed to be consumed by agents (e.g. for memory formation, dreaming, search)

Graph database native to the cloud. Embedded, multi-tenant, built on object storage.

Identity, memory & collaboration platform for AI agents — facts, memories, secrets, and inter-agent messaging via a CLI, MCP, and a Go server.

Verified experience for AI agents: independently checked, scoped, cited, and reversible.

The live network for high-quality Agent Skills — discover the latest verified versions, publish your own, and communicate agent-to-agent via MCP.

Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.

Give any MCP-capable agent persistent memory: remember/recall over a tiered store with hybrid vector + keyword retrieval. Single Go binary, SQLite or Postgres, embedded admin UI.

Safe write access for AI agents. An append-only business fact store with an MCP server: every change is kept, attributed to the agent that made it, and can be undone.

Git-native memory for coding agents. Repo memory before the diff.

The governance layer for LLM-maintained Markdown wikis.

Mission working memory for LLMs: named session graph (GQL) — cue, bounded pin_map, gated mutate. Not chat SSOT, not RAG/GraphRAG, not a DB proxy.

Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.

Minimal CLI agent framework with compounding project memory — gets smarter with every session. Clean, modular, any LLM provider

Python framework for horizontally-scalable, agent-native apps. A three-tier cache — SQLite, NATS KV, PostgreSQL — keeps state coherent across pods. Observable by default.

Persistent memory for AI agents

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

the trust layer for agent memory

Open-source TypeScript framework for persistent human-agent collaboration, with shared artifacts, human approvals and controlled execution on your infrastructure.

Self-hosted MCP server that makes your Obsidian/markdown vault searchable — text, PDFs, Office docs, images, audio — from any MCP client. Hybrid retrieval over a typed, governed corpus, sub-second at 50k notes; your files stay plain markdown.

The intentional memory layer for your AI agents.

Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.

A minimal, extensible, agent-native knowledge repository that keeps shared context current and inspectable

Local-first engineering memory for AI coding: a git-native graph of decisions, bugs, and invariants, exposed to Claude Code via MCP.