diff --git a/README.md b/README.md index 1ff08bb96..12d01198d 100644 --- a/README.md +++ b/README.md @@ -2369,6 +2369,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to - [soolaugust/0CompactMem](https://github.com/soolaugust/0CompactMem) [![soolaugust/0CompactMem MCP server](https://glama.ai/mcp/servers/soolaugust/0CompactMem/badges/score.svg)](https://glama.ai/mcp/servers/soolaugust/0CompactMem) 🐍 🏠 🍎 πŸͺŸ 🐧 - Persistent memory MCP server with OS-style demand paging, kswapd-style eviction, and mlock pinning. Multi-agent shared SQLite store with BM25 + FTS5 retrieval, importance scoring, and capacity-aware reclaim. 5 tools: `memory_lookup`, `pin_memory`, `unpin_memory`, `memory_stats`, `list_pinned`. `uvx --from git+https://github.com/soolaugust/0CompactMem memory-os` - [adelinamart/robrain](https://github.com/adelinamart/robrain) [![adelinamart/robrain MCP server](https://glama.ai/mcp/servers/adelinamart/robrain/badges/score.svg)](https://glama.ai/mcp/servers/adelinamart/robrain) πŸ“‡ 🏠 🍎 πŸͺŸ 🐧 - Self-hosted decision memory for AI coding agents. Passively captures architectural decisions with the alternatives you rejected (structured `rejected[]`), then warns the agent before it re-proposes a rejected approach. Postgres + pgvector; cross-tool across Claude Code, Cursor, Copilot, and Codex. Install: `npx robrain up && npx robrain install`. - [a2cr/a2cr](https://github.com/a2cr/a2cr) [![a2cr/a2cr MCP server](https://glama.ai/mcp/servers/a2cr/a2cr/badges/score.svg)](https://glama.ai/mcp/servers/a2cr/a2cr) 🐍 ☁️ 🏠 🍎 πŸͺŸ 🐧 - MCP server for AI-agent handoffs. Saves client-encrypted WorkBaton checkpoints and WorkStash notes so Codex, Claude Code, Roo Code, and other MCP clients can resume work without passing full chat history. +- [afairai/afair](https://github.com/afairai/afair) [![afairai/afair MCP server](https://glama.ai/mcp/servers/afairai/afair/badges/score.svg)](https://glama.ai/mcp/servers/afairai/afair) 🐍 🏠 🍎 πŸͺŸ 🐧 - The open-source, self-organizing memory for all your AI tools. Three frozen verbs (remember/recall/observe); background agents extract entities, resolve conflicts, consolidate and decay, so the vault structures itself instead of only storing. Append-only, content-addressed, encrypted (SQLCipher), single-tenant, self-hostable. `uv run python -m afair` - [ahmetakyurt/zipmem-mcp](https://github.com/ahmetakyurt/zipmem-mcp) [![ahmetakyurt/zipmem-mcp MCP server](https://glama.ai/mcp/servers/ahmetakyurt/zipmem-mcp/badges/score.svg)](https://glama.ai/mcp/servers/ahmetakyurt/zipmem-mcp) πŸ“‡ 🏠 - Local-first long-term memory for terminal AI agents (Claude Code et al.) via Anchored Compacting. Stores blueprints, code anchors (fileβ†’lineβ†’concept), and distilled lessons in a single JSON under `.zipmem/`, restoring full cross-session project context at near-zero token cost. No DB, no API keys, no embeddings. `npx zipmem-mcp` - [ihorponom/agentpack](https://github.com/ihorponom/agentpack) [![ihorponom/agentpack MCP server](https://glama.ai/mcp/servers/ihorponom/agentpack/badges/score.svg)](https://glama.ai/mcp/servers/ihorponom/agentpack) πŸ“‡ 🏠 🍎 πŸͺŸ 🐧 - Repo-native task continuity for AI coding agents: a reviewed task-state ledger (decisions, dead ends, evidence, checkpoints) in `.agentpack/` that any next session or client resumes from. - [thomasjumper/agentbay](https://github.com/thomasjumper/agentbay) [![StremAI MCP server](https://glama.ai/mcp/servers/thomasjumper/agentbay/badges/score.svg)](https://glama.ai/mcp/servers/thomasjumper/agentbay) πŸ“‡ ☁️ 🏠 - StremAI: shared memory for AI coding agents. What one agent learns, every agent recalls, across sessions, machines, and tools. Per-agent attribution, provenance, and export, so you can see which agent learned a fact and whether it has been verified. Remote Streamable HTTP with OAuth, stdio fallback. `claude mcp add --transport http stremai https://stremai.com/api/mcp`