Designing, evaluating, and shipping autonomous AI agents.
7681 posts
OASiS — an open-source multi-physics and multi-code framework for verified computer simulations. Model Context Protocol (MCP) server connect...
Deterministic, file-anchored toolkit for AI-agent work — context you can query, rules you can enforce, state you can derive.
Search, preview, and analyze datasets from 20+ platforms via a single MCP connector. Works with Claude instantly.
AxonFlow governance for OpenClaw agents — block dangerous tools, govern MCP access, and keep audit trails for production agent workflows
Cross-agent memory SDK. Agents publish lessons, query shared knowledge, with built-in redaction. Python + TypeScript.
Open-source security gateway for MCP tool calls — blocks secret leaks, enforces agent policies, and requires human approval for risky action...
The world's first MCP gateway that learns — intelligent federation, caching, cost tracking, and SLM memory integration
Self-hosted lifecycle platform for software powered by Claude Code. Configurable pipelines, devices you control, no credentials on the serve...
Browser automation, one binary. The simpler alternative to Playwright — no Node, no Python, no runtime. Library, CLI, MCP server, and chat U...
Fast Lean 4 proof feedback for coding agents. CLI, Python library, and MCP server with warm LeanInteract sessions and cached env reuse.
Drop requirements docs → AI agents debate → structured specs with @implements in 7 languages.
Command-line interface for Declaw — security-first sandboxing for AI agents
