Python agents

An risk prediction LLMs system that analyzes 31 multi-dimensional domain signal.

Ask questions about your PDFs, grounded in what's actually in them. FastAPI + Postgres/pgvector RAG API with background document ingestion, source-cited answers, and pluggable LLM/embedding providers.

Daedalus - Agentic platform for collaborative defect resolution

MCP-native AI agent OS — Redis bus, squad service, multi-model engine. Connect any agent with one URL.

Security-first multi-agent orchestration plugin for Claude Code — classifies every command by risk, gates state-changing operations behind consent, injects project context, and routes work to specialist agents. One unified plugin.

Multi-agent LangGraph orchestrator: a Telegram brief becomes a deployed project (code, CI/CD, domain, SSL) built by isolated Claude Code / Factory.ai workers.

LLM-assisted modeling for OpenModelica: an open-source, headless Python agent that turns a natural-language task into a verified Modelica model

Agentic planning for Vision-Language-Action robotics — orchestrating SmolVLA/LeRobot policies with LangGraph for multi-step robot manipulation.

A practical 12-week Agentic AI learning roadmap covering LLM foundations, tool calling, RAG, memory, MCP, multi-agent systems, evaluation, security, and production deployment.

Combine agent harnesses: Grok Build / Claude Code / Cursor as the thinker, Antigravity CLI + Cline as workers, over MCP. Clone it and plug in your own top-level agent. Early / not stress-tested — PRs welcome on the dev branch.

Relay code changes through isolated plan, build, review, and fix tasks in Codex App.

Agentic AI-powered marine intelligence platform for conversational access to ocean, weather, PFZ, risk, and route information.

A video editor an AI agent drives, running on your own machine.

A Windows 11 computer-control agent that gets its own desktop and its own cursor — so it works while you keep using yours. Claude computer-use + PySide6.

Autonomous coding agent built on LangGraph + deepagents. It natively plans, builds, verifies, and ships real production changes with a built-in human-in-the-loop review stage.

Evil Hermes — sovereign agent framework by Lord Tanzeel Shujah Khan. Cyber-security tooling, automation, and adversarial research.

Search ISRO's Bhoonidhi satellite archive in plain language from any AI agent — a MCP server built on the bhoonidhi-downloader SDK.

gguf mergekit merge text-generation en dataset:lemonilia/LimaRP

gguf gemma4 mtp speculative-decoding draft-model llama.cpp

A runtime assurance kernel for LLM-based systems: graded verdicts, hashed commitments, bit-identical replay.

An agentic AI–powered IaC scanner that evaluates cloud infrastructure against security and compliance benchmarks. It also delivers cost analysis and AWS Well-Architected recommendations, with support for custom policies, checks, and configurable exceptions.

多代理编排器，主代理分配任务给子代理

Production-grade federal law RAG with multi-source retrieval (U.S. Code, CFR, Case Law), LangGraph orchestration, hybrid search, conflict detection, and Prometheus observability. Regression-tested by Rag-eval.

AETHER — an open protocol for AI agents to discover, negotiate, and pay each other. Ed25519-signed, JSON-native, zero-dependency.

gguf llama.cpp pebble mamba2 hybrid small-language-model

Ask your AI assistant real questions about your data and get answers you can rely on — an MCP server with 45 analysis tools that pick the right statistical method themselves and tell you how much to trust the result.

Self-hosted AI execution agent for Discord: runs shell commands and edits files on your hosts, drives browsers, schedules jobs and delegates to sub-agents, within per-user host access, a command governor and an audit log. Web management UI. Works with a ChatGPT subscription, OpenAI-compatible APIs or Ollama. Desktop app: Odin Desktop.

Multi-server MCP-based AI agent with LangGraph, supporting tool-augmented reasoning, RAG (ChromaDB + Ollama embeddings), web search (Tavily), market data (Yahoo Finance), weather APIs, and a modular multi-server architecture.

Open-source multi-agent research platform — Planner, Researcher, Critic & Synthesizer agents with human-in-the-loop approval, per-claim citations, and BYOK support. Built with LangGraph, FastAPI, Next.js.

DPBench: A benchmark for evaluating coordination in multi-agent LLM systems under simultaneous resource contention.

Production-ready AI voice assistant built with FastAPI, LLMs, STT/TTS, multi-agent orchestration, and tool calling.

Friday — a governed agent kernel for Frappe. Agents act as themselves, under their own roles, with every decision audited.

Evidence-governed knowledge infrastructure for enterprise AI agents, with approved sources, traceable facts, review-gated publication, and agent-ready context.

Self-correcting agentic RAG over 2k arXiv CS papers: Neo4j · Qdrant · LangGraph

A beautiful code agent GUI with graceful agent design.

Event-driven RL Framework for Long-horizon Control in Asynchronous, Discrete-event Systems

Make any agent harness token-native.

Local-first memory for AI coding agents that catches a mistake before it repeats. Plain Markdown + git, zero deps, every agent via MCP/hooks. Formerly Anamnesis.

Production-ready multi-agent PDF RAG system with LangGraph, FastAPI, React, reflection/retry, citations, evaluation, and LLM cost observability.

Codex plugin for durable agentic software-factory orchestration with SQLite-backed ledgers.

Self-hosted agent for infrastructure

Local, read-only AI agent that investigates SIEM alerts (Wazuh) with an on-device LLM via Ollama and writes an enriched triage report for a human analyst

YOLO-Agent is an evidence-driven autonomous optimization harness for object detection | YOLO-Agent 是一个面向目标检测的证据驱动自主优化 Harness

transformers gguf bible rag question-answering qwen3.5

Versioned scientific modeling engine and Agent Skill with Model IR, simulation, fitting, uncertainty, causal/Bayesian inference, formal/numerical validation, reproducible export, REST, MCP and CLI.

Reverse-engineered async Python client for chat.qwen.ai — text chat, streaming with real-time reasoning, tool calling, image and video generation. No official API key required (works anonymously).

Security-first agent harness built for long horizon research and work capabilities with increased focus on math, computer science, and domain science research

Your personal AI assistant—built to remember and grow with you. Easy to start. Yours to evolve.

Journal-entry testing AI agent for auditors (ISA 240 / AS 2401). Import a CSV of journal entries, get a risk-ranked review universe + a professional audit report (PDF/Excel). 10 deterministic rules, AI-assisted priority ranking, hash-chained auditor decisions. No-code console; runs locally, free-tier AI.

Safely expose legacy SOAP/WSDL systems to AI agents as typed, schema-validated, audit-logged MCP servers

docker openenv region:us

transformers safetensors qwen text-generation custom_code zh

gguf text-generation nvfp4 fp4 moe qwen35moe

Self-hosted RAG event assistant (Llama 3.3 70B via Ollama, LangChain, FAISS, Gradio) - built as a 2-person sprint, deployed to production for a corporate client

Memory observability for LLM agents—trace what they remember, why, and how it shapes every response.

Real-time desktop floating token monitor and performance telemetry capsule for Google Antigravity (CDP sniffing, 5-segment breakdown, TTFT & tok/s)

A Codex plugin that reduces over-design, hidden failure, and evidence inflation in research engineering.

FinSight：可追溯、可修订的多 Agent 金融研究工作台，支持研究图、可编辑 Skills、原生运行记录与多格式报告。 | A financial research workspace with traceable evidence, human revision and editable agent methods.

Agent-agnostic evidence-bound memory and handoff side-car for multi-agent systems. Claims carry checksummed excerpts — verified means re-verifiable, stale evidence gets flagged. MCP server, CLI, and git hooks. Apache-2.0.

MC-GPT: say the outcome in English or German. Task, Meeting and Multi-Coder for Claude, Codex, Gemini, Grok and Ollama. Docs + AI index: https://iotaitech.github.io/MC-GPT/ · llms.txt

docker region:us

transformers safetensors llama text-generation conversational bg

transformers gguf heretic uncensored decensored abliterated

gradio region:us

transformers gguf text-generation en base_model:Qwen/Qwen2.5-Coder-7B-Instruct base_model:quantized:Qwen/Qwen2.5-Coder-7B-Instruct

A Home Assistant integration providing a Retrieval-Augmented Generation (RAG) AI agent with configurable backends.

tqdm-style progress bars in the Claude Code statusline for any long-running job. Claude picks how to observe progress; the ETA corrects itself; crashes come back with a skull and a report.

ACE — Agentic Context Engineering: evolving, self-improving context playbooks for LLM agents. Faithful ICLR 2026 implementation with OpenAI Agents SDK support.

ASF. A lightweight framework for running AI agents in constrained, policy-controlled environments. The agent gets only what you explicitly allow.

gguf agentic code imatrix merge qwen3.5

Autonomous coding agent built on LangGraph + deepagents. It natively plans, builds, verifies, and ships real production changes with a built-in human-in-the-loop review stage.

An AI-powered coding assistant fine tuned for local light-weight LLMS with enhanced features for file management, terminal integration, testing, code refactoring, and project management.

Scio — the encyclopedia for agents, written by agents. Every sentence shows its source. The plugin and skill for any agentic harness.

MCP server for code structure analysis across 20+ languages. Tree-sitter powered. Works with Claude Code and Claude Desktop.

An independent benchmark for the Tiiny AI Pocket Lab. Measures what the box actually does: prefill scaling, sustained throughput, concurrency and reasoning cost, with NPU budget as the currency. Web app plus a self-contained HTML report. Python stdlib only.

Give an AI agent full remote control of a Windows PC - with zero console windows flashing on screen. 让 AI 完全操控你的 Windows 电脑，屏幕上不闪任何黑窗口。

Opinionated, portable agent skills and instructions with installer script for Claude Code, Codex, Cursor, Gemini, and Grok. One directory (~/.agents), installed by symlink.

Microsoft Graph MCP server for AI agents — 85 tools across Outlook mail & calendar, Teams, OneDrive, SharePoint, OneNote, Planner and Entra ID. Delegated OAuth, stdio or Streamable HTTP.

Trusted architecture context for AI agents: an evidence-backed architecture graph from OpenAPI, AsyncAPI and OpenTelemetry, served over MCP.

一个好用的文件解析skill，支持pdf、work、ppt、图片，一键转成智能体能识别的markdown文本

An open-source AI infrastructure profiler that connects AI workload telemetry to physical infrastructure behavior and economics.

gradio mcp-server region:us

transformers pytorch jax safetensors llama text-generation

面向 A 股的日频量化研究与回测引擎，支持传统因子 + ML推理 + Python函数混合策略

T2AG 是考你而不是替你答的 AI 学习框架：错题、证明与每一次裁决都存在归你所有的纯文本里，任何 agent 可读可带走；环上的裁决者是你。An AI learning harness that tests you instead of answering — your mistakes, proofs and verdicts live in plain text you own, portable across agents; the judge in the loop is you.

Open Source Desktop AI Agent Runtime - LLM, MCP, Voice Runtime, and local/cloud models wired into one PyQt6 desktop agent (Ollama + Hermes)

Context-driven valuation bias and halo effects across six multimodal LLMs (companion study to Lee, 2026)

JMP — Joint Model Participation. A local coding workspace where Jev routes actions and OpenAI, DeepSeek, or local models generate arguments.

Post-response grounding check + cross-family adversarial review for LLM chat agents

Lightweight long-term memory retrieval for chat agents using NPMI + Hebbian learning — no vector database or embedding model required.

Relation-aware, calibrated and provenance-preserving context routing for interleaved agent conversations

Cursor for the physical world, Connecting AI to the physical world. 物理世界的Cursor，连接AI与物理世界

Temporal context, CRUD tools, and automated deduplication for Mem0 OSS + Qdrant. Fixes time-blindness and conflict resolution gaps.

Open source runtime to migrate DRF to FastAPI (and more to come) 🚚

ORCH: Organizational principles enable collective intelligence in embodied AI

Safe Multi-Agent Deployment Platform: pairwise safety analysis for autonomous agents that share a filesystem, clipboard, and OAuth scopes. Every verdict is graded on a four-rung evidence ladder, from docs-only to executed-in-sandbox.

Agentic AI platform for financial analysis featuring specialized for annual report understanding, company comparison, financial fundamentals, ML-based prediction, and Retrieval-Augmented Generation (RAG), built with Python, LangChain, Ollama, ChromaDB, and Streamlit.