Lists (22)
Embedded/DIY
finance
[ML/AI] Agentic
[ML/AI] Collections
ML/AI - Embeddings
[ML/AI] Frameworks
[ML/AI] image/video generation
[ML/AI] LLM infer/optimize
[ML/AI] LLM models - coding
[ML/AI] MCP servers
[ML/AI] Optimization
[ML/AI] preprocessing
[ML/AI] quantization
[ML/AI] RAG
[ML/AI] Reinforcement Learning
[ML/AI] UIs/Apps
[ML/AI] vision
ML4Sec
remarkable
[SEC] Fuzzing
Security
UI frameworks
Stars
Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.
AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill memory for cross-task skill reuse and evolution.
Open-source AI hackers to find and fix your app’s vulnerabilities.
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
MiniMax-M2, a model built for Max coding & agentic workflows.
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Hierarchical Reasoning Model Official Release
Codes/Notebooks for AI Projects
Python package and backend for the Elysia platform app.
A Hardware Hacking Tool with Web-Based CLI That Speaks Every Protocol
"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.
This repository collects and organises state‑of‑the‑art papers on spatial reasoning for Multimodal Vision–Language Models (MVLMs).
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
A tiny, dependency-free computer vision library in C for embedded systems, drones, and robotics.
Orchestrate Claude Code, Codex, and Gemini sessions on a multiplayer canvas. Manage git worktrees, track AI conversations, and visualize your team's agentic work in real-time.
Official implementation of "Continuous Autoregressive Language Models"
An early research stage expert-parallel load balancer for MoE models based on linear programming.
A calm, CLI-native way to semantically grep everything, like code, images, pdfs and more.
LLM Council works together to answer your hardest questions
Run Claude Agent (Claude Code) in a sandbox, control it via websocket
Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc
Cybersecurity AI (CAI), the framework for AI Security