Python agents

🔥🔥🔥EMNLP 2026 Main🔥🔥🔥 EvLink: Source-grounded evidence linking for Graph RAG

A self-hosted, widget-first RAG knowledge base for websites — throw your web pages and local files at it, and it'll answer with cited sources😶‍🌫️.

transformers gguf text-generation base_model:google/codegemma-1.1-7b-it base_model:quantized:google/codegemma-1.1-7b-it license:gemma

A FastAPI backend template for services that are built and maintained by coding agents

Family Tree AI Assistant — GEDCOM → Neo4j → Multi-Agent AI → Web + WhatsApp

File-based Sol-Grok handoff skill for persistent cross-conversation implementation and review workflows.

Spec-Anchored Agentic Development — methodology + ready-to-install Claude Code bundle: one permanent spec per capability, machine gates before human review, autonomy as an evidence-gated gradient

面向 Markdown、DOCX、PDF、LaTeX 和纯文本科研论文的 Codex Skill，用于结构化预审研究问题、变量、方法、证据、图表、附录和引用一致性。

An outcome-first operating framework for reliable AI agent work.

Production harness and control plane for accountable AI-assisted software delivery

Provenance-tracking firewall that stops LLM agent prompt injection (OWASP LLM01) via token-level taint analysis — a zero-trust, deny-by-default guard on privileged tool calls.

Deterministic blast radius for every change. Verified impact on every PR, self-updating architecture docs, autonomy earned via eval scores.

Autonomous COBOL to Python migration using AI agent swarms. 226 tests. pip install cobol-moderniser

Create Comic with Plan anywhere. Render anywhere. Resume everywhere.

多平台AI私信Multi-platform DM aggregation tool

MCP-native knowledge-graph memory for AI agents

AI-powered Telegram assistant built with Python, Google Gemini, LangChain & LangGraph, featuring agentic tool calling, conversation memory, and modular AI architecture.

A small, sanitized starter for building a durable AI company brain with clear approval boundaries.

The official UI design & interactive prototyping foundation for the TidyFactor Ecosystem.

One toolkit, every agent — drop decentralized, all-TEE, OpenAI-compatible Chutes.ai inference into Claude, Hermes, OpenClaw, Codex, or any OpenAI-compatible client.

A 100% free AI pipeline that researches, scripts, narrates, and uploads faceless YouTube videos — one command

Local-first Apple Health bridge for AI agents

Persistent memory for Home Assistant Assist, in plain markdown. No vector DB, no embeddings — works with Anthropic Claude, OpenAI, and any LLM conversation agent.

A collection of original skills independently designed and developed by Anna Tchijova, grounded in scientific methodology and established engineering best practices.

FreeAI: Unified AI Inference Workstation — local LLMs, autonomous agents, full SDLC automation, security tools, and multi-provider routing. One self-hosted stack.

Agentic RAG system for analyzing legal contracts. Chat with agreements, extract clauses, flag risks, and compare terms using a local LLM.

Your coding agent says "done." Godmode is how you know: a local, tamper-evident evidence ledger of what it did, claimed, and verified - with gates and a completion bar enforced in hooks at runtime. Zero deps, zero network. Claude Code, Grok, Codex, OpenCode, Antigravity.

A Python CLI coding agent powered by remote Ollama, with workspace inspection and command-execution tools over Tailscale.

AI agent for video production — text/image-to-video generation, avatar/UGC talking-head videos, and data-driven ad-creative remakes, powered by muapi.ai.

codex docs

Diagnosis-first, reversible Skill for Codex Reconnecting 1/5 through 5/5 loops

Profile Claude Code context, discover repeated workflows, and regression-test your skills. Local-only, zero-dependency.

safetensors qwen3 speculative-decoding dspark dflash draft-model

This AI Agent collects data from sources like Database connection, API connection, Direct CSV/XSLX file upload; cleans & preprocess it; can query data using custom SQL commands through NLP chatbot; visualizations are provided; and a final Report is generated at the end. It acts as a accessory tool for a Data Analyst.

LLM context compression proxy — 40-70% token savings, zero code changes

Kill AI slop in agent writing. Skill + hooks that make Claude, Codex, and Grok write like a person: direct, active voice, no filler, no fake structure. Local digest of the Google developer style guide.

transformers gguf mistral quantized 2-bit 3-bit

transformers.js onnx qwen2 text-generation conversational base_model:Qwen/Qwen2.5-Coder-0.5B-Instruct

Local-first desktop app (macOS & Windows) to chat with your own projects — offline RAG over your files, grounded answers with sources. No cloud, no accounts.

Turn Spark/Hive SQL into structured, traceable facts for Agents, RAG, and AI knowledge bases.

智能PDF转换器，可针对每种文档类型自动选择最佳引擎（Docling/MinerU/PyMuPDF4LLM）。无需任何配置即可获得最佳的Markdown和Word输出效果。

Self-hosted, self-learning, provider-agnostic personal agent kernel. Local-first memory in one SQLite database, project-scoped, reachable from any tool over MCP or a CLI.

🥗 AI Nutrition Assistant / AI 智能营养师 — Photo food recognition, AI nutrition analysis & personalized dietary advice. 拍照识别食物、AI 营养分析、个性化膳食建议的全栈应用。

Own your AI memory, don't rent it. A native Claude Code skill AND a standalone, zero-dependency MCP server over one local SQLite file. git clone and go — full-text knowledge graph, plain-markdown, you own the data.

🚀 An intelligent, LLM-enhanced log parser pipeline that converts multi-format raw logs into structured JSON, learns from missed patterns, and evolves using Drain3 & open-source LLMs.

数学建模竞赛/项目端到端 Agent Skill：选题·数据审计·建模验证·制图·论文·提交审计

Claude Code as a second brain: all 101 skills, a working CRM engine, vault templates and the handover map. Method, not data.

Local-first AI orchestration platform for N8N - LLMs, workflows, image/video generation, TTS, and music in one portable folder. No install. No Docker. No admin rights.

人文社科 AI 研究技能库 — human-in-the-loop research skills for Codex, Claude Code, and OpenCode.

An open-source agent flow from natural language spec through Verilog RTL and UVM verification to front-end signoff on commercial EDA tools

Operating system for humans and AI agents to jointly initiate, execute, approve, and reconcile work under explicit authority

A Git-native federation and governance profile for organizational knowledge bundles based on OKF.

Device connector for AgiMate: connects a macOS, Windows or Linux machine to your agents as a fixed set of tools and triggers

Sync your NotebookLM notebooks to Obsidian automatically via a multi-agent LLM pipeline.

Audit-and-falsify agent framework for quantum-computing research — 13 skills, paper-audit chain, quantum-CS fallacy taxonomy, real token+USD ledgers

Sandboxed security scanning for AI skills and MCP servers — precise findings, heatmap posture, fail-closed agent guard. Multi-scanner security platform for AI skills and MCP servers, scan what the agents install!

面向 Windows 桌面的 Codex 宠物运行时，用于承载、展示与驱动由 Codex 生成的桌面宠物交互体验。

Mode-based local Skill environments for Codex, Claude Code, and DeepSeek Harness.

Data-driven blog content pipeline for AI agents. Keyword research → content gaps → SEO writing → GEO optimization → publish. Works with OpenClaw, Claude Code, or any agent.

Open-source runtime security for tool-using AI agents. Control risky actions, enforce policies, and keep audit trails for MCP and agent workflows.

The official open-source repository for community-built prototypes and tools powered by the Oxlo API

LAMA CARAVAN — Local And Multi-backend Adaptive Computation And Routing Across Various AI Nodes. Self-hosted control plane for llama.cpp fleets and AI agents: hybrid local/cloud token routing with queues & schedules, remote server cells, HF model browser, usage accounting. Stdlib Python.

Parallel model rotation across any CLI. Auto-discovers models, health-checks in <2s, scores by capability+cost, picks the best for every task.

Governed software development for AI coding agents.

Doc-driven AI-agent skills for COMSOL, ANSYS, AutoCAD, and SOLIDWORKS automation.

A fast multi-threaded Instagram username availability checker with Telegram notifications. Hunt for rare usernames with random generation or batch checking from lists.

AI-powered marketing automation toolkit built on Claude Code subagent orchestration. Autonomous workflows for content creation, campaign management, SEO, lead generation, and browser automation.

Turn goals, existing Skills, and authorized work records into bounded Agent Loops, then export a Codex Skill or Compact Prompt with separate verifiable evidence.

Sleep-time memory consolidation for Claude Code agents, with a cross-project shared-consciousness layer.

Top 420 Viral GitHub Repositories (2026) : 20 for overall and 20 for each of the 20 categories i.e. 20*20+20 = 420

Local-first operating layer that decomposes long AI work into executable tasks, routes them across models and tools, and keeps human decisions in the loop.

Steel (steel.dev) cloud browser provider plugin for Hermes Agent

Testing and evaluation framework for AI agents

BonoBox (BBX): useful tools for AI agents and everyday automation — real tests, clear limits.

Read-only-first Codex skill for auditing and refactoring existing skills

Multi-agent LLM peer review: an editorial board for manuscripts. Eight specialist reviewers, an advocate/skeptic debate, an author rebuttal, and an editor's verdict, with full reports at every stage.

Chunking that understands who is speaking. Parse any transcript, chunk it without ever splitting a speaker turn. Zero dependencies.

Grounded perceptual memory for personalized agents: VLM grounding, specialist identity encoders, and a training-free in-model attention bank. Paper: arXiv:2608.28609

Live token usage & cost HUD inside Codex App. Renderer-injected, fully local, zero telemetry.

类脑联想记忆库：SQLite + bge-m3 + 扩散激活的单机记忆引擎。纯向量回答'哪条最像'，联想记忆回答'这整件事是什么'。Brain-inspired associative memory engine (spreading activation, online learning, flexible forgetting).

Orchestrator/sub-agent RCA system with a production-grade eval and observability harness — LangGraph agents, Ragas/Promptfoo evals, OTel tracing.

Production-shaped control plane for AI support agents: scoped routing, policy broker, tool boundaries, approval queue, replay verification, audit traces, and human handoff. Prototype on synthetic/sample data — no production users.

Deterministic observation-integrity contracts for AI-agent tool results. HTTP 200 is not an observation.

OneBot 11 adapter for Hermes Agent (NapCat / go-cqhttp)

AI-powered WhatsApp receptionist that books appointments via Google Calendar. Built with FastAPI + Claude API.

Run an open-source repo as its maintainer: triage the tracker, delegate the work, review hard, merge on green. One loop, one version, and per-repo differences in config instead of prose.

Setup your RAG agent using FastAPI with this ONE package!

An autonomous AI Operating System for coding, automation, creative generation, and intelligent task execution.

你的私人摄影指导团队

🌍 Agentic geopolitical risk analyzer — discovers second-order asset exposures through historical evidence, not LLM hallucination. Agent proposes, deterministic layer verifies. LangGraph + ChromaDB + FastAPI.

Local, private prompt optimization with DSPy and Ollama. Rewrites prompts, measures them against your own data, and evolves them from feedback with GEPA.

A self-improving weather forecasting & trading agent, in public.

Your AI agent writes code — but does it know WHY your code exists? Decision provenance, quality contracts, and AI anti-pattern detection for coding agents. 19 languages. MCP compatible.

Embeddable agent runtime and workbench for teams that need sandboxed execution, host integration, platform governance, and reusable AI infrastructure.

AI-powered SEO article generator with agent-based pipeline — SERP analysis, editorial briefs, hybrid quality scoring, multi-provider consensus (Claude + Gemini), and automated edit loops

基于 DeepSeek Harness + AKShare 的本地 A 股 AI Agent 工作台：数据获取 / 每日晨报 / 交易复盘三大技能，只做分析、不做交易。

Drop-in operating systems for knowledge workers. Product Manager OS: 53 skills scored 100/100 in CI, an operating brain, a memory that learns your product, and a loop that builds you new skills from the work you repeat. Runs on Claude Code, Cowork, Codex, Cursor, and Gemini CLI.

Persistent knowledge and validation-gated skill evolution for coding agents, based on arXiv:2608.27454.

Drop-in .claude/ config that turns Claude Code into an autonomous academic paper production system. 6 agents, 47+ skills, 5-phase pipeline from literature search to submission-ready manuscript.

An Autonomous AI Agent with a custom MCP server that does Duolingo for you and sends Discord notifications when done