www.opensourceprojects.dev/post/a510bb...
10.03.2026 02:30
👍 0
🔁 0
💬 0
📌 0
A terminal tool that right-sizes LLM models to your system's RAM, CPU, and GPU. Detects your hardware, scores each model across quality, speed, fit, and context dimensions, and tells you which ones will actually run well on your machine
Your group chats contain years of data.
ChatLab turns them into a dataset.
Run SQL queries, let an AI agent explore patterns, and analyze millions of messages locally without sending your data to the cloud.
Turn a single gpu into an autonomous ai research laboratory
Building RAG systems usually means stitching together 10 different tools.
OpenRAG bundles everything into one stack.
• document ingestion
• semantic search
• agentic workflows
• chat over your data
Powered by Langflow, Docling, and OpenSearch.
Before you contribute to a GitHub repo, check its health.
repo-health analyzes things like:
• commit activity
• issue response time
• documentation quality
• community signals
Then generates a health score to show if the project is worth your time.
What if an entire engineering team was just AI agents?
SWE-AF spins up a fleet of agents that can plan, code, test, review, and ship production-grade pull requests from a single goal.
AI agents analyzing stocks together.
That’s the idea behind AlphaCouncil.
A multi-agent stock analysis system that pulls data from Gemini, DeepSeek, and JH Data APIs to generate market insights and decision support.
Odin gamedev is getting interesting.
Karl2D is a simple 2D game library focused on minimal dependencies and a clean workflow for shipping games.
Definitely worth exploring.
900+ battle-tested agentic skills for AI coding tools like Claude Code, Cursor, Codex, and Gemini.
Architecture, security, DevOps, AI, testing… all organized and ready to use.
If you’re building AI agents, this is a goldmine.
The open-source AI-native security testing platform built in Go.
It integrates 100+ security tools, an intelligent orchestration engine, role-based testing with predefined security roles, a skills system with specialized testing skills, and comprehensive lifecycle management capabilities.
Select the perfect ai model from 41 options in under a millisecond
Create mesh security providers for any network with this protocol
IronClaw is built on a simple principle: your AI assistant should work for you, not against you.
In a world where AI systems are increasingly opaque about data handling and aligned with corporate interests, IronClaw takes a different approach
Build a company that runs itself using this open-source automation engine
