Open Source

AWS Labs methodology and adaptive rule set that turns any AI coding agent (Claude Code, Cursor, Copilot, Q Developer) into a disciplined SDLC-aware engineering collaborator.

MIT-0190

TrendingAgent

GitHub

30.9K2.6K

PageIndex

VectifyAI

Vectorless, reasoning-based RAG framework that builds hierarchical document trees and lets LLM agents navigate them through reasoning instead of vector similarity.

TradingAgents

Tauric Research

Multi-agent LLM framework from Tauric Research that simulates a trading firm with specialized analyst, researcher, trader, and risk management agents collaborating through structured debate.

agentmemory

rohitg00

Open-source persistent memory for AI coding agents with 95.2% R@5 retrieval, 92% fewer tokens, and 51 MCP tools.

OpenHuman

tinyhumansai

Local-first open-source personal AI assistant in Rust with Memory Tree, 118+ OAuth integrations, and TokenJuice compression.

DeepSeek TUI

Hmbown

Rust-based terminal coding agent for DeepSeek V4 models with streaming reasoning, 1M context, MCP support, and workspace rollback.

FastGS

fastgs

CVPR 2026 Highlight: trains 3D Gaussian Splatting scenes in roughly 100 seconds with multi-backbone acceleration.

QwenPaw

agentscope-ai

Open-source personal AI assistant on AgentScope runtime, supporting local and cloud deployment across major chat platforms.

TokenSpeed

lightseekorg

Speed-of-light open-source LLM inference engine targeting TensorRT-LLM performance for agentic workloads on Blackwell GPUs.

ik_llama.cpp

ikawrakow

Community-maintained llama.cpp fork delivering SOTA quantization (IQ_KT trellis, IQK family, MXFP4), FlashMLA for DeepSeek, and substantial CPU + hybrid GPU/CPU speedups for local LLM inference.

SageAttention

thu-ml

Tsinghua's SageAttention delivers 2-5x quantized attention speedup over FlashAttention with no accuracy loss, supporting Hopper, Ada, Ampere, and Blackwell GPUs across language, image, and video models.

DeepEP

deepseek-ai

DeepSeek's expert-parallel communication library delivering high-throughput MoE dispatch/combine kernels with FP8 support, NVLink + RDMA backends, and JIT-compiled GPU kernels for SM90 Hopper.

MIT272

ikawrakow

Community-maintained llama.cpp fork delivering SOTA quantization (IQ_KT trellis, IQK family, MXFP4), FlashMLA for DeepSeek, and substantial CPU + hybrid GPU/CPU speedups for local LLM inference.

SageAttention

thu-ml

DeepEP

deepseek-ai

DeepSeek's expert-parallel communication library delivering high-throughput MoE dispatch/combine kernels with FP8 support, NVLink + RDMA backends, and JIT-compiled GPU kernels for SM90 Hopper.

MIT272

12 13 14 15 16 17 18 19 20

15 16 17 18 19