Sealbook / Open source / AI agents & LLM apps

magnitudedev/magnitude

Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Works on Apple Silicon, NVIDIA, AMD, or just a CPU.

GitHub ↗Website ↗

License & maintenance

Apache-2.0 is a permissive license: free to use commercially with attribution.

Last code push today.

Similar projects

	Repository	Stars	Language	License	Activity
1	morluto/reaReverse engineer anything with agents, from app behavior down to native binaries.	★ 319.5k	TypeScript	MIT	Active
2	mattpocock/skillsSkills for Real Engineers. Straight from my .agents directory.	★ 296k	Shell	MIT	Active
3	affaan-m/ECCThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Code	★ 283.1k	JavaScript	MIT	Active
4	NousResearch/hermes-agentThe agent that grows with you	★ 254.9k	Python	MIT	Active
5	deepseek-ai/deepseek-harnessDeepSeek Harness: Everything is a Plugin.	★ 253k	TypeScript	MIT	Active
6	multica-ai/andrej-karpathy-skillsA single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.	★ 220.9k	—	—	Slowing
7	anomalyco/opencodeThe open source coding agent.	★ 216.3k	TypeScript	MIT	Active
8	n8n-io/n8nFair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integ	★ 207.9k	TypeScript	Other	Active