The private, owned conversation-memory layer for AI. Record, transcribe, and search every meeting.
Storage, memory and knowledge management for agents.
The private, owned conversation-memory layer for AI. Record, transcribe, and search every meeting.
Personal testing fork of flameY3T1/tm1-mcp-server (npm: tm1-mcp-server). Use the original.
MMPL (Memory Palace) Rust Edition — 单二进制 DuckDB 记忆 MCP Server (9 工具 + ONNX 语义向量 + 冲突双通道门控 + 场景构建 + 四层钻取) — Linux + Windows 双平台
AI-powered browser automation MCP — 6 tools for web interaction, extraction, and validation.
Verified coding workflows with planning, verification, bounded retries, evidence, and evolution.
Persistent memory for AI coding agents — local embeddings, SQLite stores, zero config. Works with OpenCode (as a plugin), Claude Code (as an MCP server), and Cursor (as an MCP server).
Production TypeScript & JavaScript AST code analysis and risk assessment MCP server.
Auditable, conserved AST code intelligence for AI agents. JS/TS, Python, Go, Rust, Java, C/C++, C#.
Local cognitive identity engine with traits, behavioral evidence, and revision history.
Memory interface for coding agents — stable memory_* tools over Hindsight, mem0, or Cognee.
Persistent sequential thinking MCP — chain-of-thought reasoning that survives sessions, resumes across agents, and saves conclusions as plan artifacts. Powered by ZeroDB. Zero-config: agents self-provision a ZeroDB account on first run, no signup required
deja-vu memory for pi: the coding sessions already on this machine — pi, Claude Code, Codex, Cursor and 39 more — recalled at session start and on every prompt, searchable with /deja. A local index, no LLM.
Code Graph MCP Server
Learnlog MCP: ask your AI assistant what learning records actually show about help. Read-only tools for Learnlog records, QLM credential verification, and QLM's public misconception and learning-graph datasets.
Local relationship model and social CRM for contacts, relationships, evidence, and commitments.
deja-vu memory for opencode: the session history of forty-two other coding agents, searchable and recalled on every request — a local index, no LLM.
Find features you built in other projects, see how they fit this one, and reuse them.
Architecture docs from a repo: overview, modules, API surface, routes, dependency graph, diffs.
Cerefox — user-owned shared memory for AI agents. CLI + stdio MCP server + web UI + ingestion for a knowledge base on your own Supabase project (or fully self-hosted with Cerefox Local).
Free-to-start portable memory for AI agents: encrypted, shareable, provably erased. Join SAIHM.