Python agents

A local 'second brain': RAG over your scattered notes and docs, with an MCP server so AI agents can use it too.

Agents that read the web through Lyrenth and finish the job: one command, cited answers, and steps that can write the result to a file.

Typed sync/async Python client for the Lyzr RAG service (PepGenX and Lyzr-hosted deployments)

Official Python SDK & CrewAI Tools for M2MCent

M2MCent x402 V2 plugin for LangChain (EIP-3009 Gasless Settlement on Base L2, 1,062 Micro-Services, Vouch Grade A).

M2MCent x402 V2 plugin for LlamaIndex (EIP-3009 Gasless Settlement on Base L2).

Design-rule governance for agent projects: skills, CLAUDE.md, MCP configuration and each project's own rules, with levels, exemptions and reports for CI.

A maf-sandbox router as a Deep Agents sandbox backend — any backend the router admits (Docker, ACA Sandboxes) behind LangChain's BaseSandbox, with the router's isolation floor and egress policy still enforced.

AIGP governance adapter for the Claude Agent SDK (agent-loop level: query/ClaudeSDKClient, tool use). Distinct from aigp-anthropic, which wraps raw Messages API calls.

AIGP governance adapter for Microsoft Agent Framework (MAF) — the converged Semantic Kernel + AutoGen SDK (GA 2026-04-03)

AIGP governance adapter for the OpenAI Agents SDK (agent-loop level: Runner.run, tools, handoffs). Distinct from aigp-openai, which wraps raw chat completions.

AIGP governance adapter for semantic-kernel

Managed Agent SDK (Python) — 控制面支持腾讯云 API 与 WorkBuddy OpenAPI，数据面使用 ACP

Embedding backend for manicule that runs the model on an Ollama server.

Multi-agent evaluation and reasoning trace extraction for scientific workflows

Math AI Agent that uses LLM + Rubens calculator-mcp.

MCP server that provides Google Search via Gemini's built-in Grounding with Google Search feature.

An MCP terminal adds capabilities to an agent

Discriminative Monte Carlo Tree Search using TypeSafe Jev System One Primitives and Gemini

OpenAI Agents SDK adapter for MemSandbox

Amazon Bedrock AgentCore Runtime adapter for Memanto persistent memory (preview)

Mercado Pago Checkout Pro via Orders API for commerce-agents

MetaCar 多车协同场景 Python 扩展接口

Bottom-up, open-source optimization tool for planning mini-grids in remote areas.

Evidence-backed dependency migration assistant (experimental alpha)

终端里的编码 Agent：配置驱动，支持 OpenAI Chat / Responses 与 Anthropic 协议、MCP、Agent Skills

A minimalist coding agent

Mistral Agents SDK - build and serve agents in Python

OTLP-first Mistral AI observability SDK

Qdrant plugin for Mistral Search Toolkit

Mistral Vibe Harness runtime & bindings

Version control for AI agent memory. Python SDK for Mnemosyne.

LangGraph BaseStore backed by Mnemosyne: versioned agent memory with blame and branch.

Webhook-managed OpenAI Agents API sessions in Modal sandboxes

Find local AI models that fit your hardware, with memory and speed estimates.

AI Agent Framework, the Pydantic way

The official capability library and harness for Pydantic AI

AI Agent Framework, the Pydantic way, slim package

Pluggable open-source agentic memory layer — MRAgent (arXiv:2606.06036)

A crash-proof, autosaving prompt editor for AI coding agent CLIs — compose in your real editor, hand off with a slash command

Local multi-provider LLM proxy, model router and control plane for Claude Code, Codex, OpenCode, Gemini CLI and other AI coding agents: 57 providers, fallback routing, credential health, a native web-search tool proxy, and analytics with cost provenance

A terminal coding agent with tool calling, context management, subagents, MCP, and skills.

GitHub Issues REST polling channel for Nagents

Telegram Bot API long-polling channel for Nagents

A coding agent with zero runtime dependencies. Stdlib-only Python.

AI evidence engine that detects financial claims in Indonesian market narratives and verifies them against Sectors v2 financial data

MCP server exposing the Naragate reality-gap evidence engine to any MCP-capable agent (desktop, CLI, IDE).

Agent Skills (SKILL.md) management for LangChain: middleware, progressive-disclosure tools, and composable loaders

Independently maintained ndspy fork with additional Nintendo DS format support.

Agent client for NEURA Compute: OpenAI-compatible inference where the agent pays for itself. HTTP 402 -> wallet sign-in -> USDC on Base -> credited -> retry, as a drop-in http_client for the OpenAI Python SDK.

NeuralTrust TrustGuard security components for Haystack pipelines

Auditable, provider-neutral RAG for newsroom research

Python SDK for NexaSwarm autonomous revenue swarms

Name reservation for a private GrowIT package. No public releases; importing this placeholder raises ImportError on purpose.

Official Python SDK for NEXIUM Storage

Async Python SDK for the Nexus nxs agent runtime

A small, local, message-driven coding agent.

Python SDK for protecting autonomous AI-agent actions with Nodra.

An open agent harness for the nonprofit sector: review gates, budget ceilings, readiness scoring, and a pluggable model layer. Built on Google's ADK, usable without it.

LangChain integration for RustChain — check balances, list bounties, node health, current epoch

An ultrafast browser agent with a dynamic, indexed action space.

Generated Python protobuf messages and Connect clients for the O11y One AGENTIC domain (agentic + common only). A per-domain subset of o11y-one-api so agentic-only consumers do not carry the other domains. Generated from proto at PROTO_PIN — do not edit by hand.

MCP server for Obsidian vaults — Dataview, Tasks, Templater, Excalidraw, Omnisearch

Call the Ollama local API by function.Please install Ollama before use.

OpenAI-compatible Moderations API gateway backed by Ollama (Cloud or self-hosted)

A terminal coding agent, built from scratch in layers.

Your computer, piloted by any LLM. A cross-platform, provider-agnostic, permission-safe computer-use agent (OpenAI, Anthropic, Gemini, NVIDIA NIM and 10+ more).

Execution safety for side-effecting AI agent tools.

one — autonomous terminal agent (CLI + TUI + JSON-RPC); optional human cooperation mode

Provider-agnostic reference commerce agent — a fork of anthropics/commerce-agents that runs on any OpenAI-compatible chat-completions endpoint (OpenRouter, Chutes, LiteLLM, vLLM, self-hosted).

Persistent Python, long-lived sub-agents and a continual harness for the coding agent you already use

Verifiable execution receipts for OpenAI Agents SDK agents. Every tool call mints a verifiable AER-1 receipt at zambo.dev.

OpenAI-compatible HTTP API for the deepgrove/maple-preview reasoning model

A fork of the OpenAI Python SDK with optimized request transforms

An unofficial drop-in OpenAI Python SDK with a local SQLite response cache

Open AIoT (开放AIoT) MCP Server — the open standard interface between AI and physical devices. Namespace placeholder; source at github.com/Open-AIoT/mcp.

A local-first, auditable personal AI agent runtime

OpenTelemetry Amazon Bedrock instrumentation

OpenTelemetry Official DSPy instrumentation

OpenTelemetry LlamaIndex instrumentation

OptiVision RAG: Extreme Token Compression for Vision-Language Models

Record a LangGraph run's own structure — which node ran, in which superstep, and how it ended — into an OrcaReplay trace.

Record the OpenAI Agents SDK's own run structure — agents, handoffs, guardrails — into an OrcaReplay trace.

DeepAgents bridge: thin shells over ordigovernance tracked atoms

LangChain/LangGraph bridge: thin format-translation shells over ordigovernance tracked atoms

OpenAI-compatible endpoint bridge for the Orditect ecosystem: governed LLM calls with audit, budget, and observability (bridge reference implementation)

Otto: a terminal AI agent built around measured results -- one agent loop, a rubric-first evaluator, tiered memory, multi-vendor routing, and six benchmark harnesses.

Autonomous Agent Package for Ouro

Dialog transformer for OVOS, designed to return responses from Ollama

Beeswarm and quasirandom geoms for plotnine

Palabra Realtime STT/TTS models for the OpenAI Agents SDK VoicePipeline

Client for pankhllm, the LLM gateway that learns to skip the LLM.

The LLM gateway that learns to skip the LLM: trains its own tiny decision model on your agent's traffic and answers repeat decisions in 0.2 ms with no LLM call. OpenAI-compatible, one Rust binary. The server binary for pip users: pankhllm serve

Configurable local runner for Papaya agent-client jobs

Calling a local model about a paper, and keeping what the call cost: tool-submitted answers, truncation discipline, and a row per call.

PASM 智能体集 —— 基于 PASM 引擎的成品智能体：游戏 NPC / 老人陪伴 / 学习陪伴 / 智能客服 + 七个长期验证智能体

RAG (Retrieval-Augmented Generation) reutilizável sobre bases de conhecimento em Markdown

Typed async and synchronous Python clients for Pi's agent RPC runtime

Pinpoint APM Python agent