The best-benchmarked open-source AI memory system. And it's free.
Repository Index
47,133 repositories indexed
1–19 of 19 · Most stars
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
- apple
- cua
- lume
- macos
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
#1 Persistent memory for AI coding agents based on real-world benchmarks
ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with AI coding assistants such as Antigravity, Codex, and Claude Code. It also achieves 99%+ success rate on AndroidWorld Benchmark.
This repo hosts Prowler OSS (CLI and Local Server). Prowler is the world’s most widely used open-source cloud security platform that automates security and compliance across any cloud environment for Humans and AI Agents.
- security
- security-tools
- security-audit
- security-hardening
TranslatedOpen-source AI API relay benchmark, rankings & switcher for Claude Code / Codex: measured availability, latency and price
One 8 KB skill that replaces REA (Reverse Engineer Anything): plain CLI tools, no MCP. Benchmarked: 38% faster, 35% cheaper.
UNIGIT public brand and ecosystem hub — AI should work for everyone.
- agentic-ai
- ai-tools
- ai-workbench
- ecosystem
TranslatedLearning notes and tooling skills for AI video
- ai-video
- claude-skills
- ffmpeg
- shot-analysis
GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard | Fable 5 Level Coding for a Fifth the Price - or on a Single GPU
TranslatedMulti-scenario AI workbench: six-layer master outline + topology wiring diagram + public-version workbench templates (four scenarios can run, source code can be copied and used as is) + memory mechanism. Companion marketplace: https://www.mydsh.xyz . Author: https://linyujia.me . Note: it does not work as soon as it is installed; the scenarios need to be tuned to your own content.
Translated流儀 (Ryugi, "style" or "school of practice") — a skills collection for coding agents and the artifacts workbench they design in: live artboards, commentable documents, HTML test benches, TDD builds
Tips & tricks to tune .NET workloads for better perf (mostly, targeting benchmarks).
- diagnostics
- dotnet
- performance
- profiling
Multi-agent research execution system: paper reproduction, benchmark evaluation, AutoResearch and claim-evidence graphs
- auto-research
- golang
- multi-agent
- paper-reproduction
Mobile runtime detection workbench for AI (iOS and Android)
- frida
- reverse-engineering
- android-security-tools
- frida-gadget
A Consistent Data Visualizer for Agents and Humans
PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.