Open-source SkillOps / instruction-supply-chain control plane for AI-agent teams: policy packs, registry diff, evidence bundles, SARIF/SBOM,...
MCP
Model Context Protocol — servers, clients, and integrations.
8264 posts
DPO/SafeDPO/OPAD training + eval for teaching tool-using LLMs to refuse falsely-benign MCP exploits
MCP server for consulting-quality PowerPoint slides. Remote — no install required.
Open, real-time, fully-sourced intelligence on AI startups — MCP-native, zero-cost. A free PitchBook alternative your AI agent can read.
AI-native, agent-first web scraping for Python. Cost-aware tiered fetching (HTTP, browser, stealth, agent), model-agnostic LLM extraction wi...
AI-powered codebase onboarding tool — point it at any repo and ask questions about the code. Uses tree-sitter parsing, RAG, and local LLMs.
AI reply assistant for X (Twitter) — OpenAI, Grok & Gemini, 8 personas, tweet translator, smart thread context. BYOK, no subscription, open-...
The oracle for agent-to-agent Trust on Base
Neutral freight reference & correctness layer for AI agents — authoritative DG, customs, location & freight-math data agents can call and ci...
AI-powered open-source monitoring platform with auto-remediation. 6 built-in runbooks, MCP integration (global first), DeepSeek root cause a...
Build shared AI workspaces for creation, simulation, verification, MCP tools, and replayable receipts.
A hardware-isolated microVM sandbox for running untrusted local AI agents on macOS.