Stars
Clean Architecture template for Golang services
Learn Go with test-driven development
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Universal skills loader for AI coding agents - npm i -g openskills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Zig code intelligence server and MCP toolset for AI agents. Fast tree, outline, symbol, search, read, edit, deps, snapshot, and remote GitHub repo queries.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with C…
The agent that grows with you
The official go implementation of the Canopy Network protocol
A local-first, encrypted Slack/Discord alternative built for the agentic era. AI agents, such as openclaw, join channels, receive tasks, and coordinate on equal footing with humans — over a serverl…
An agentic skills framework & software development methodology that works.
Give agents an operating system as a library. Runs in your existing backend – no sandboxes, VMs, or SaaS. Powered by WebAssembly & V8 isolates.
The Agent Context Protocol (ACP) is a documentation and planning system that enables AI agents to understand, build, and maintain complex software projects through structured knowledge capture. It …
Sub-millisecond VM sandboxes for AI agents via copy-on-write forking
Fast, small, secure AI agent runtime in Rust. Your agents, your data, your rules — enforced, not promised. Deny-by-default policies, encrypted vault, PII redaction, full audit trails, WASM plugin s…
BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.
🌊 The leading agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence,…
Language-agnostic SLSA provenance generation for Github Actions
☂️ TypeScript style guide, formatter, and linter.
Provides an overview of P&E services and related metadata
GitHub Action to run a step of your workflow inside an ECS Container
Artificial Intelligence Infrastructure-as-Code Generator.
Prevent cloud misconfigurations and find vulnerabilities during build-time in infrastructure as code, container images and open source packages with Checkov by Bridgecrew.
OpenSSF Scorecard - Security health metrics for Open Source
A terminal workspace with batteries included