PyPI agents

Reserved for Omnigent community use and to prevent malicious use.

Omnis — a multi-agent harness: CLI/TUI (omnis) + HTTP API & Web UI server (omnis-server).

Python SDK for OpenMemory and Hermes AI integration

CLI for GitHub AgentOS — provision label-driven multi-agent orchestration

Auto-generate a governance ontology, Trust Profile, and signed badge for any agent, MCP server, repo, OpenAPI, Rego, or workflow. The OpenTelemetry for agent governance.

188 Scavio real-time search tools over 31 platforms (Google, YouTube, Amazon, Walmart, eBay, Target, Zillow, Booking.com, Indeed, SEC EDGAR, G2, Meta Ad Library and more) for the OpenAI Agents SDK

OpenAI Agents SDK tools for Signatrust — cryptographically signed, tamper-evident AI Decision Receipts.

Build your own Ziwei or Qimen agent on the OpenAI Agents SDK - hosted astrology models plus your own local tools, MCP, and human-in-the-loop.

OpenBox SDK - Governance and observability for CrewAI agent workflows

Coverage path planning for UAV aerial surveying

跨交易所资金费率套利系统

OpenTelemetry LiteLLM instrumentation

Production-grade Harness Agent built on top of LangChain Deep Agents.

Coinbase AgentKit action provider for OSF (Open Source Filings): provenance-stamped sanctions, entity, and CVE data for AI agents, paid per call over x402 (USDC on Base).

Pull open-weight AI models from the ossllms torrent network. An HF-cache-compatible download shim for common huggingface_hub public model pulls.

Catch the LLM/AI calls you didn't need. A fast, deterministic linter that flags LLM API calls where plain code is simpler, cheaper, and more reliable.

Governance patterns for autonomous AI agents in health-insurance / payer operations (aligned to the NAIC Model Bulletin framework)

Governance patterns for autonomous AI agents in regulated payments

Haystack converter for pdfmuse — deterministic PDF/DOCX parsing for RAG.

PDO (Python Do) — a terminal-first AI agent that reasons, plans, and safely executes real tasks.

Pipecat community TTS integration for the XTTSv2-vLLM streaming server

pirn agents domain knots.

Diagnose and repair why your LLM traces aren't showing up in PostHog.

EU AI Act-compliant scaffold and utilities for automating ingest PRs with GitHub Copilot

Governance patterns for autonomous AI agents at SEC-registered investment advisers (private capital)

General agent runtime with a built-in ProseForge writing workflow pack.

Circuit breaker SDK for LLM agents.

King County, WA civic data tools for pydantic-ai agents — no API keys required

Mimir persistent, local, encrypted memory for Pydantic AI agents — exposed as a Toolset.

FanLang — LangChain integration. OODA Agent and FanLang Retriever for LangChain apps.

LLM-powered semantic assertions for pytest

Python bindings for QueryMT Agent

Host-agnostic, self-correcting library/API memory daemon for coding agents (Qwen MemoryAgent)

FANUC RAG Knowledge Base — pluggable retrieval + SAG hybrid search + OKF concepts

Red-team your RAG pipeline for prompt injection and source-document leakage, in CI.

SDK Python oficial do RAGaaS (ragaas.com.br) — RAG, memória de agente e gateway OpenAI-compatible

Semantic-velocity document chunker — cuts where meaning changes, then snaps to real sentence/paragraph boundaries.

A clean-architecture RAG library with graph orchestration, multi-provider LLMs, and a low-code facade.

Local-first, top-tier RAG over your notes, docs, and PDFs — answered by Claude.

Universal RAG framework SDK for Python developers

Scan your AI's vector database for exposed sensitive data.

A modular Retrieval-Augmented Generation (RAG) pipeline for Python.

pytest for RAG agents — behavioral audits with PASS/FAIL/WEAK verdicts

An MCP which adds terminal capabilities to an agent.

Plug-and-play agentic framework with multi-backend, guardrails, and Azure AD support

Reserved for RECKON (reckon.bet). Coming soon.

rehuco PySide6 desktop GUI

一个极薄但生产级的单-agent harness 框架:5 行把任意大模型变成能调工具、自己循环干活的 agent

RelintioAgent in-process agent for Python ASGI runtimes.

Google Gemini oracles for Robot Framework: text-only and multimodal (image) assertions.

AI-powered ROS 2 development assistant

High-performance autonomous agent engine powered by Rust and Python.

AI-агенты как сущности: автономный онбординг инструкций (идемпотентные managed-блоки в .claude/.cursor/.codex/.gemini/.github/…) поверх единого реестра агентов-данных. Тонкий слой на clikit.

Объектное хранилище (ObjectStorage protocol + MinIO adapter + image normalization for Skillery)

Agent-first lightweight CI/CD tool

A conversational AI agent for your notes — Obsidian, Notion, and more — via MCP.

A LangGraph-based multi-agent SDLC orchestration library

A MCP which adds terminal capabilities to an agent`

Semos Agentura - umbrella package installing the full multi-agent suite (MCP + A2A)

Shared MCP + A2A base classes for Semos Agentura agents

Document digestion (OCR to Markdown) and composition (Markdown to documents) agent

Unified email client (IMAP/SMTP + Outlook COM) with LLM agent and archive

Virtual filesystem with multi-root VFS, SharePoint WebDAV, archive browsing, and MCP/A2A agent

Panel-based chat client for Semos Agentura MCP agents

Sernixa local MCP discovery agent

AI-powered autonomous web security scanner with real-time streaming — enterprise DAST platform

An MCP which adds terminal capabilities to an agent

A local, free, self-fact-checking multi-agent research assistant (Ollama + MCP + RAG).

Estimators for skill formation models

A coding agent with history-bounded, task-elastic reconstructed context — built for long-horizon work.

AutoGen adapter for Snubber

CrewAI adapter for Snubber

LangChain adapter for Snubber

LangChain BaseChatModel adapter for somm — lets LangChain/LangGraph/deepagents apps use somm as their LLM substrate

Policy-first OpenAI-compatible gateway for regulated workloads

A beginner-friendly Python SDK for building step-based agent workflows.

Lightweight structured output runtime for Python LLM calls.

Official name reserved by the MiroShark project. See the repo.

Skill-aware agent wrapper for Swarmauri.

AWS IAM Identity Center OAuth 2.0 / 2.1 login implementations for Swarmauri

Salesforce OAuth 2.0 / OAuth 2.1 / OIDC 1.0 identity provider implementations for Swarmauri

Deterministic in-memory Swarmauri billing provider for testing, examples, and full billing capability contract checks.

Stripe-backed Swarmauri billing provider for checkout, payments, subscriptions, invoices, refunds, disputes, Connect, and webhooks.

Deprecated standalone compatibility package for canberra distance.

This repository includes experimental components. (Inactive: experimental packages are now standalone.)

DPoP proof-of-possession tooling for Swarmauri services

X.509 mutual TLS proof-of-possession verifier for Swarmauri

Drop-in state backend for LangGraph, CrewAI & custom agent loops - Rust core, framework-agnostic, built for production.

A smart, OpenAI-compatible LLM router — a tiny triage-verify-escalate agent that saves cost without losing quality.

Let your LLMs call each other — a local MCP switchboard for coding agents

CLS observability SDK for OpenAI Agents SDK — 6-layer span hierarchy, direct upload to Tencent Cloud CLS

CLS observability SDK for vLLM — FastAPI middleware intercepts LLM requests, direct upload to Tencent Cloud CLS

Termux AI Agent - 智能终端助手，支持多平台AI(DeepSeek/阿里云百炼/硅基流动)，JSON模式工具调用、文件精确编辑、插件系统、智能搜索模式、后台任务处理、对话历史

RAG job pack for Tessera: compile a corpus + queries into a validated retrieval eval dataset.

Text-interface LLM control plane for semcod/coru shell automation (pair with gillm for GUI).

LangChain retriever for trelix code intelligence

LlamaIndex retriever for trelix code intelligence

Use TensorRT-LLM models from LangChain (ChatTrtLlm) with model load/unload and streaming

Tsugite plugin: Claude Code provider (routes LLM calls through the claude CLI)

Governed agent runtime adapters for Tuning Engines, LangGraph, Temporal, and MCP.