Agentic Version Control System — an AI-native VCS where intent, session, operation, evidence and decision are first-class objects and code is a materialized projection of an operation graph.
Research-grade investment decision engine for AI agents: isolated multi-agent committee, auditable verdicts, backtests with lookahead protection, published negative results
An AI-driven dynamic protocol fuzzer for the Model Context Protocol (MCP). Prove runtime exploitability by discovering state violations, transport crashes, and application-layer logic flaws (SSRF, LFI) before your AI agents do.
Self-hosted retrieval infrastructure for AI assistants. MCP-first search and grounded answers over a private corpus, with citations that resolve to a real location in a real document — a page, a heading, a line, a cell.
31 MCP tools that give Claude, Cursor and any MCP client the live web — scrape, crawl, search, real Google rank, change tracking, document parsing, plus an autonomous agent that researches from a plain-English prompt with no URLs. Clean Markdown and schema-validated JSON, not raw HTML. Local-Ollama extraction by default. MIT, 1,000 free credits.
Local MCP server that helps coding agents stop re-reading the same code every turn. Repository intelligence, cache-write optimization, and long-term session memory. 100% local. No API keys.
Code search that lets AI coding agents find the right files in fewer steps. Use the hosted endpoint or self-host, works with Claude Code, Copilot and Cursor via MCP.
saige - Super Artificial Intelligence Graph Environment. A unified Go SDK, CLI, and MCP server for streaming AI agents, knowledge graphs, and RAG pipelines, with Ollama, OpenAI, Anthropic, and Google providers behind one interface.
Slack MCP server for Claude Code, GitHub Copilot, Cursor, JetBrains, and any MCP-compatible client. Morning recaps, decision detection, multi-channel digests.
Claude Code QA agent with memory, plus a read-only MCP server (verdict-qa-mcp on PyPI): baseline → delta runs (NEW/REGRESSED), a fact harness so the model judges while the system measures, signed run history, flaky quarantine with expiry, and an exit-code release gate for CI. Ships six scored eval fixtures — misses published.
The self-correcting memory layer for AI agents. Zero-dependency Python memory and MCP server. Supersede, revert, or forget a value deterministically. Verifiable erasure, witness-backed tamper-evident receipts, EU AI Act ready.
TrainingPeaks MCP server for Claude Desktop, Code and Cowork. No API approval needed - works with any account. Query workouts, CTL/ATL/TSB fitness data, power PRs via natural language.