TRENDING

Goose is a Rust-built AI agent with a CLI, desktop app, and API that runs against 15+ LLM providers and extends through 70+ MCP extensions - here is why developers are installing it.

Headroom is a context compression layer that intercepts your AI agent's tool outputs and strips 60-95% of the tokens before they hit the model - with benchmarked accuracy preserved.

Headroom is an open-source context compression tool that reduces tokens sent to LLMs by 60-95%, available as a Python library, proxy server, or MCP server - with no code changes required.

Headroom is a context compression layer trending on GitHub that slashes token usage by 60-95% across Claude Code, Cursor, and other AI coding agents - without sacrificing accuracy.

HKUDS/CLI-Anything hit 40,000 stars by solving a stubborn gap: most desktop software has no interface AI agents can reliably drive. Its 7-phase pipeline auto-generates a tested CLI harness from source code.

A practical framework for building LLM-powered software that actually ships to production customers - not just demos. 21.8k stars and still climbing.

Anthropic just shipped an official curated plugin directory for Claude Code. It earned 2,500+ stars in a single day and changes how you extend your AI coding workflow.

CodeGraph builds a local SQLite index of your codebase so Claude Code, Cursor, and Codex CLI spend far fewer tokens exploring files - trending on GitHub with 12k stars and real benchmark numbers.

CodeGraph hit 7,800+ stars with 1,900 added in a single day - a local MCP knowledge graph that lets Claude Code explore codebases with drastically fewer API calls.

The humanlayer/12-factor-agents repo distills hard-won lessons from shipping AI agents into 12 concrete principles. It crossed 21,000 stars on GitHub this week.

humanlayer/12-factor-agents crossed 20k stars with a simple argument: most AI agents fail in production because they ignore decades of software engineering wisdom. Here are the twelve principles fixing that.

obra/superpowers is a composable skills framework for coding agents that turns vague requests into structured, test-driven development - and it runs across Claude Code, Codex, Cursor, and Gemini CLI.

agentmemory is a self-hosted MCP server that gives Claude Code, Cursor, and Gemini CLI searchable long-term memory across sessions - with 12 auto-capture hooks and 51 tools, no external database required.

obra/superpowers picked up 1,600+ GitHub stars in a single day by solving the real problem with coding agents - they skip the boring parts that make software actually work.

obra/superpowers enforces a seven-step development loop - brainstorming through branch completion - across Claude Code, Cursor, Gemini CLI, and five other agent platforms.

Matt Pocock's Claude Code skills library picked up 3,372 GitHub stars on a single day. Here's what's inside, how to install it, and whether the skills hold up in real projects.

Matt Pocock's .claude skills directory hit 74.7k GitHub stars, offering structured workflows that address the four most common ways AI coding agents fail.

agentmemory gives AI coding agents a persistent brain - capturing session context automatically via 12 Claude Code hooks and 51 MCP tools, with 95.2% retrieval accuracy and 92% token savings over context-pasting.

Ruflo is an open-source multi-agent orchestration platform built specifically for Claude, shipping 100+ specialized agents, vector memory with HNSW indexing, and zero-trust federation across machines.

AgentMemory hit GitHub's daily trending list with 400 new stars today, offering a persistent memory layer for AI coding agents that benchmarks at 95.2% retrieval accuracy on LongMemEval-S and 92% token reduction.