#Python

NVIDIA

earth2studio

★ 1,131

Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.

stephenschoettler

hermes-lcm

★ 1,124

Lossless Context Management plugin for Hermes Agent, DAG-based context engine that never loses a message.

flagos-ai

FlagGems

★ 1,121

FlagGems is an operator library for large language models implemented in the Triton Language.

ansible-collections

community.general

★ 1,067

Ansible Community General Collection

fuyuxiang

echo-agent

★ 1,056

Echo Agent 是一个可自托管、长期运行、持续学习的 AI Agent，面向个人与团队的私有自动化场景。它可以部署在自有服务器上，统一连接模型、工具、记忆、权限与消息入口。内置四层认知记忆、遗忘曲线与矛盾检测机制，能够在跨会话任务中持续沉淀上下文，并保持长期记忆的质量。针对命令执行、文件操作等高风险行为，它提供基于 LLM 的审批与解释机制，为关键操作建立可审计、可追溯的安全边界。原生支持 MCP、A2A、多模型路由、任务调度、工具调用和多通道接入，覆盖 CLI、Gateway API、微信、Telegram 等入口。它让 Agent 带着长期记忆和可进化技能，持续、安全地为你工作。

jowilf

starlette-admin

★ 1,032

Fast, beautiful and extensible administrative interface framework for FastApi & Starlette applications.

abrignoni

ALEAPP

★ 918

Android Logs Events And Protobuf Parser

agentforce314

clawcodex

★ 899

Token efficient Claude Code full Python rebuild. AI Coding Agent in 270K LoC pure Python. Up to 200X Cost Saving!

pydantic

pydantic-ai-harness

★ 891

Batteries for your Pydantic AI agent. Pydantic AI core ships capabilities that require model or framework support, and capabilities fundamental to every agent web search, tool search, thinking.

Skyvern-AI

rustwright

★ 888

Playwright's API on a Rust CDP engine, Chromium browser automation for Python & Node, no driver subprocess. (Alpha).

CodeAbra

iai-personal-memory-engine

★ 883

A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.

jjang-ai

vmlx

★ 851

vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!

flosell

trailscraper

★ 838

A command-line tool to get valuable information out of AWS CloudTrail.

LvcidPsyche

auto-browser

★ 792

Give your AI agent a real browser, with a human in the loop. Open-source MCP-native browser agent.

dongshuyan

compass-skills

★ 726

司南：个性化 AI 任务总控 Skills 系统 /COMPASS: Personal Alignment Skills OS for AI Agents

mikehasa

agentacct

★ 720

See what your coding agents did and what it cost. Breaks each task down into work steps, tools used, files changed, tests run, time and tokens spent. Local-first dashboard for Claude Code, Codex, OpenCode, and more. No login, no telemetry.

staruhub

ClaudeSkills

★ 713

13 curated Claude Code agent skills, decks, deep research, PRDs, articles, audits. Tested like software.

zli12321

LHTB

★ 702

Long Horizon Terminal Benchmark with Dense Reward Grading. Grok 4.5 tops the board at ~$11/task, and cheaper models like MiniMax M3 ($6/task) and Hy3 ($2.47/task) are competitive with models costing 5 10 more (Claude Fable 5 at $73/task, Claude Sonnet 5 at $60/task).

YoungCan-Wang

WyckoffTradingAgent

★ 606

Open-source Wyckoff trading agent and AI stock screener for volume-price analysis, A-share screening, CLI workflows, and MCP tools. trader @Hoyooyoo.

Ikalus1988

MisakaNet

★ 491

📚 A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. Python stdlib only. |