跳到主要内容
GitStars
登录

03 / Leaderboards

开源项目排行榜

按 Star、近期活跃度与创建时间整理榜单,并可按语言或主题标签筛选;排名只反映公开仓库的客观指标,是否适合你的场景仍需回到项目档案核对证据。

30 entries · updated from public GitHub metadata

总星标榜活跃综合榜本周活跃榜本月活跃榜新晋榜

新晋榜

Python共 30 个项目
1X
xiaoyang111222/cn-math-taxonomy

数学(小学到高中)、英语(三年级到高中)、初中物理的知识图谱:1644 个知识点、2403 条先修边、6723 道题,对齐课标,附自适应前置诊断。

Python3.5k8522026.10.25NOASSERTION
2C
cranebeaker/coop-anything

Co-op Anything: point your AI agent at any single-player game and play it with friends (online and/or splitscreen!). MCP server and playbook to let you reverse engineer, fix, test, ship and share what it learns.

Python1.3k1642026.10.25MIT
3D
deepseek-ai/DeepInfer

DeepInfer: High-performance, large-scale inference framework for DeepSeek models

Python22.2k2.6k2026.10.25Apache-2.0
4M
MaryCache/imozuru

知らない分野を、原文にたどりつくまで芋づる式に掘る Claude Code のスキル

Python1.3k562026.10.25MIT
5Z
zhuyansen/new-term-radar

Daily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.

Python1.8k5492026.10.25MIT
6N
NandhaKishorM/laya

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

Python34.3k3.1k2026.10.24Apache-2.0
7A
air-embodied-brain/Zetta-Embodiment

Zetta is an efficient closed-loop embodied harness for self-evolving physical intelligence. It evolves code-based runtime critics and recovery skills online while keeping the base policy frozen. Project Page: https://air-embodied-brain.github.io/zetta/

Python1.3k842026.10.25Apache-2.0
8S
scenario-labs/skills

Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and brands consistent through the Scenario MCP, plus expert teams that drive Blender, Maya, ZBrush, Unreal, and Unity.

Python1.1k1392026.10.25MIT
9H
HarnessRouter/harnessrouter

HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.

Python3.6k3892026.10.25Apache-2.0
10A
AdamPlatin123/dsh-plugin-radar

DSH Plugin Radar — open-source ecosystem radar for DeepSeek Harness plugins: continuous discovery (21k+ candidates), k8s runtime validation (13k+ tests), 15-min snapshots; the catalog is a generated artifact — 开源 DSH 插件生态雷达:持续发现 2.1 万+ 候选、k8s 运行级实测 1.3 万+、15 分钟快照;插件目录为自动生成的产物

Python1.5k1702026.10.25MIT
11K
kirodotdev/KiroCrew

A persistent workspace for development work that self-improves and continues beyond one session.

Python4.6k8722026.10.25Apache-2.0
12O
omnigent-ai/omnigent

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

Python11.0k1.8k2026.10.25Apache-2.0
13R
rlaope/oh-my-hermes

The coding intelligence and skills for Hermes Agent ⚚ just install once. then type 'dag-ulw' to be graph engineering master.

Python4.1k3102026.10.25MIT
14L
loopx-project/loopx

Turn long-horizon goals into verifiable results. A local-first semantic control plane and research workbench for long-running agent teams, across sessions and runtimes.

Python6.4k6122026.10.25Apache-2.0
15O
odysseus-dev/odysseus

Self-hosted AI workspace.

Python94.4k1.8k2026.10.25AGPL-3.0
16A
ayghri/i-have-adhd

A skill to stop your coding agent from burying the answer. ADHD-friendly output.

Python58.7k3.4k2026.10.19MIT
17L
lightseekorg/tokenspeed

TokenSpeed is a speed-of-light LLM inference engine.

Python2.8k3762026.10.25MIT
18B
beenuar/AiSOC

Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.

Python3.7k3772026.10.25MIT
19V
virgiliojr94/book-to-skill

Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.

Python36.0k3.8k2026.10.18MIT
20C
chunxiaoxx/nautilus-compass

Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform

Python1.3k352026.10.25NOASSERTION
21I
ifixai-ai/iFixAi

Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.

Python34.2k1.7k2026.10.24Apache-2.0
22Y
Yuan1z0825/nature-skills

符合nature论文学术表达和科研绘图的Skill

Python50.5k2.6k2026.10.25Apache-2.0
23V
verl-project/verl-omni

Multimodal RL training framework for diffusion & omni models

Python1.4k2772026.10.25Apache-2.0
24D
debpalash/VoiceStudio

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

Python85.8k9.5k2026.10.25AGPL-3.0
25M
mnemosyne-oss/mnemosyne

Zero-cloud AI memory that works everywhere. SQLite-backed. One pure-Python dependency.

Python3.5k3092026.10.25MIT
26A
alchaincyf/nuwa-skill

你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.

Python35.9k4.7k2026.10.24MIT
27M
MemPalace/mempalace

The best-benchmarked open-source AI memory system. And it's free.

Python59.7k7.6k2026.10.25MIT
28G
Graphify-Labs/graphify

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

Python134.8k12.9k2026.10.23Apache-2.0
29H
HKUDS/Vibe-Trading

"Vibe-Trading: Your Personal Trading Agent"

Python36.6k5.9k2026.10.25MIT
30O
Observal/Observal

Observal is self-hosted registry for your coding agent extensions with a built in insight engine. Setup Observal, define the scope and share your Skills, MCPs and Agents with your peers.

Python4.5k1.1k2026.10.25Apache-2.0

榜单依据公开 GitHub 元数据生成,Star 数会随时间变化;活跃榜仅表示近期有推送,不代表质量评价。

用需求找仓库