FastrMemory
Local installio.github.atifjubaer/fastrmemory
Local-first cognitive agent memory with bi-temporal SQLite, replayable history, hybrid retrieval.
4,941 servers in AI & Agents
Local-first cognitive agent memory with bi-temporal SQLite, replayable history, hybrid retrieval.
Search and run hosted AI agent skills for Claude Code, Codex, Cursor and Gemini CLI.
Agent memory and a signed spending ledger: pay any x402 API, keep a provable receipt.
Optional diagnostics MCP server for OpenReflex's ambient project muscle memory.
Many stdio MCP servers from one container, published over HTTPS with OAuth 2.1 for any MCP client
Every AI chat starts already knowing your project. Needs the TruthSpine app: truthspine.app/download
Living economy for AI agents — Conway physics, energy currency, marketplace, reputation.
Cut LLM agent token use in Claude Code, Cursor, Codex, Gemini CLI. Local, no API key. gAI Ventures.
Local-first memory over MCP. Built-in SQLite store; runs standalone. Agents propose; you confirm.
Verifiable agent work contracts; separate opt-in Codex preview-directory guard.
AtlaSent for AI agents: with an API key, actions wait for approval with signed proof. No key: demo.
Drafts a network allow list for agent tools and runs them in a network-blocked sandbox.
Gateway in front of MCP tools: critical arguments are checked against trusted sources and a policy.
Persistent memory for AI agents: connects MCP clients to your Kemory memory vault
Manage persistent AI-agent filesystems. Paid hosted service; Apache-2.0 client.
Local, private memory for coding agents: facts, skills and tasks that persist across sessions.
Starter kit for small businesses: A2A agent card, MCP server card, example MCP server, validator.
Measure MCP servers, pin the approved tool surface, refuse calls to tools that changed. Local-first.
Full-text search, browse, and resume across your coding agent sessions (Claude Code, Codex, Amp)
A group chat for AI coding agents: Claude Code, Cursor, Codex, Gemini CLI, Qwen Code and OpenCode.
Pi agent teams on any provider: parallel delegates, forks, MCP tools; runs built to finish.
Governed MCP gateway: approved tools only, each call policy-checked and recorded per agent
Several models from different labs plan in a blind proposal, debate and review loop. Your own keys.
Local memory for coding agents; a rule with a proof can refuse. Full install with hooks: the repo.
Local-first, cloud-friendly memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search.
Private on-device memory & retrieval for AI assistants — offline vector + lexical search.
Verified memory for coding agents: briefed before each task, proven by checks, gated on change.
MCP control plane: discovery of servers, tools and skills, profiles, audits, gated tool gateway.
Memory database for AI agents: remember and recall over a running Fraise daemon, in FQL.