HexWitness
Local installio.github.siaginw/hexwitness
Durable, build-scoped reverse-engineering evidence memory and query tools for AI agents.
4,968 servers in AI & Agents
Durable, build-scoped reverse-engineering evidence memory and query tools for AI agents.
See what each of your coding agents is working on, and read or advance your todos.
Shared memory for parallel AI coding agents. Local, free, with rooms and file claims.
Discover funded agent work and prepare approval-gated TaskMarket delegations.
Local-first AI memory over MCP. No account; you own the store.
Live LLM pricing, context windows and model ids, read from each vendor's own page every 3 hours.
Evidence-grounded agent memory with mandatory provenance, on local SQLite or Cloudflare D1
Lossless archive and search for AI agent sessions across clients, exposed to agents over MCP.
Verifiable dealings with other agents: prove what you did, vet who you deal with, bind agreements
Govern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics.
Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.
Search and exchange troubleshooting knowledge across persistent AI-agent identities.
Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
One shared memory for every AI you use, in plain Markdown files you own.
Aggregates and proxies other MCP servers, letting LLMs discover, add, and manage tools at runtime.
Bitemporal memory for AI agents with point-in-time recall and tamper-evident audit history.
Record an agent's decisions with reasons anyone can re-execute offline — verify recomputes them.
China MCP gateway hosting HTTP APIs for Doubao/Tongyi/Wenxin/Claude; weather, currency, holiday.
Local long-term memory shared by all your AI agents, kept word for word on your own PC.
Code mode for MCP: search, describe and execute over all your servers, with a sandbox and approvals.
Price a Claude, GPT, Gemini or Grok call before you send it. Runs locally.
Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.
Runs coding-agent workers on a codebase question; every claim in the answer carries evidence.
Self-hosted gateway aggregating upstream MCP servers behind one authenticated HTTP endpoint.
Offline, read-only tools that verify AI claims against evidence and replay conformance vectors.
MCP server for Memanto - persistent semantic memory for any MCP-compatible agent
Local-first memory for coding agents — MCP server, single SQLite file, local embeddings
Memory for your agents, kept on your Mac. Needs Onadit for Mac, from onadit.com/download.
Reasonbook: decisions that survive the session, in a local record AI agents keep.
Hand tasks from Claude Code, Codex or any MCP client to a local DeepSeek Harness.