IWE (iwe.md)
Local installio.github.iwe-org/iwe
Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
4,941 servers in AI & Agents
Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
AI Agent Reliability Toolkit: evidence checks, feedback and permission-controlled local diagnostics.
An MCP server that stores Copilot customizations from the Awesome Copilot repository
Persistent Memory for AI Agents, in plain local files. No network calls of its own.
AISchemaGate validates and repairs structured LLM output against a contract, plus DataContractGate.
Long-term memory for AI agents: fast recall, project brains and skills, local, in one binary.
Governed skills, rules and commands for AI coding agents, served by a read-only MCP server.
Ask 200+ AI models privately from your agent: one-shot, chat, second opinions, prices, images.
Local 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.
Cross-harness communication and shared work-state for AI coding agents.
Local-first memory for AI agents: recall with sources, answer checks, documents, mesh, governance.
Keeps an AI coding agent on its plan across context compression, with a live local dashboard.
Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.
Start, prompt and read AI coding agent sessions (Claude Code, Codex, Gemini CLI and more) in Codeman
Wraps any MCP server: identical write-tool calls run once, and every tool call is audit-logged.
Agent control plane for DCC and engine hosts: one MCP endpoint, one tool contract.
Persistent memory for AI agents: local-first MCP server, zero-config. No cloud, no API keys.
Persistent memory for AI assistants with semantic search and knowledge graph relationships.
An AI agent's own long-term memory, on your machine. Needs a one-time: npx anairyspirit setup
Deedglass lets rules decide each AI agent tool call, checks what really changed and seals a record.
Compare recorded MCP tool definitions before reusing a saved tool selection.
Tells an AI agent when another is already doing its work. Board, typed mail, directory claims.
Ask a collection of LLMs at once through your Benchwarmers server; verdicts pick the next panel.
Local-first persistent memory for AI coding agents - 96.0% R@5 on LongMemEval, zero LLM calls.
Lets your AI agents call you when they need a decision, and hear your answer.
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.