Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
2,235
repos tracked
175
surfaced this week
194
created < 30d
Python
top language
25 repos
-
OnCo: total information dominance on cancer. A public, cited knowledge graph of oncology with a website, JSON API, MCP server and CLI: one page per cancer, treatment, target, trial, institution, person and idea, plain English first, solution and mechanism first.
-
Highlight and capture the web in your favorite browser. The official Web Clipper extension for Obsidian.
-
Local macOS context archive: Knowledge and browser history, evidence-linked correlation, CLI, and read-only MCP.
-
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
-
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
-
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
-
Release automation and evidence ledger for OpenClaw.
-
Knowledge that can show its work: an open, federated knowledge system for humans and agents.
-
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline, and other AI coding clients 逆向/渗透/安全技能路由包 - AI 自动路由 + 按需自举工具链 + 自动进化经验库 | 支持 Claude Code / Kiro / Cursor / Cline 等代码 AI 客户端
-
Cutting-edge Hyperloom fork with pinned GEAK Codex/ChatGPT subscription mode
-
Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.
-
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
-
Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.
-
EdgeBench: Unveiling scaling laws of learning from real-world environments
-
Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.
-
FrogPilot is a fully open-source, frog-themed, and highly customizable fork of openpilot, built with clean commits and a strong focus on serving the community. Shaped by both user and developer contributions, FrogPilot embraces collaborative, community-driven development to deliver a cutting-edge openpilot experience for everyone!
-
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM Computing Surveys, 2026.
-
Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.
-
World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.
-
HTTP SQLite scale-to-zero database on the edge built on Cloudflare Durable Objects.
-
FastCrest Tether: the OSS edge-to-cloud AI deploy CLI. Optimize, verify, deploy across Jetson, RTX, Apple Silicon, AMD. Hybrid edge-cloud inference with parity certs.
-
A curated collection of papers and resources on On-Policy Distillation for Large Language Models.
-
An opinionated, agentic life-OS for Claude Code — a markdown vault with daily/weekly/quarterly review skills baked in. Includes the feedback layer most templates skip.
-
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% local