Drop-in MCP proxy for debugging AI agents. Real-time timeline, replay, diff. Local-first, no telemetry, one binary.
Agents
Designing, evaluating, and shipping autonomous AI agents.
7651 posts
MCP server exposing pmcontrols (CPM, PERT, crashing, EVM, earned schedule) as validated tools for AI agents.
Sovereign MCP server: WORM chain, agent builder, Ada contracts, digital twin, Mamba SSM injections
Bring your local Gemini CLI agent into Discord as a persistent operational presence.
Multi-tool LLM agent benchmark: 496 end-to-end MCP tasks, deterministic evaluation, Russian localization
MCP & Claude Code security scanner — threat-models plugins, MCP servers, hooks, skills & connectors with an LLM before you trust them. Catch...
Local-first multilingual memory for Codex, Claude Code & MCP — immediate durable reports, exact-ID + hybrid recall, Qdrant + Ollama.
Offline Diablo II: Resurrected toolkit for save editing, character creation, creating your own mods, and MCP integration for agentic clients...
🧠 Mnema — Long-term memory for AI via MCP × Vector DB. Solves the context-window problem with pluggable vector backends (Chroma/Qdrant/sqli...
Agent-driven, reviewable safe-commit layer for Office files: circle a region, say what you want, review the diff, high-fidelity write-back....
Eyes for AI coding agents: deterministic MCP server that tells the LLM which CSS rule wins, in which file, on which line — and why. Cascade...
App-store market intelligence for AI agents over MCP: competitor sets, studios, share-of-search, rank movement. Public endpoints, no API key...