Python agents

MeshRAG: Multi-Knowledge-Base Graph RAG, based on LightRAG

Instrument your own AI agents (LangChain, CrewAI, OpenAI Agents SDK, or plain Python) for Metano: session telemetry and runtime guardrails.

Name held by Metergraph. Contains no functionality; see the README for the package to use.

Name held by Metergraph. Contains no functionality; see the README for the package to use.

MetisPrism setup helper: shows how to install MetisPrism tools from your account and checks your local Python and GPU setup.

Hybrid System-One Local Decision Engine (JevCompat 32/32 MUST, AnyJev L0 Prefill, StartLux Read-or-Think Cascade, OpenJev-RLCD Trainer)

Fast MiMo-V2.5-ASR inference and OpenAI-compatible serving with vLLM

Explore how frontier models use a browser in fewer than 400 lines of Python.

MintID agent client: agent credential custody, witness refresh and the x402 payment-identity loop over the MintID holder library

Python SDK and CLI for the Mirasoth AgentSpace API - isolated cloud workspaces for agent execution

The HTTP delivery machinery apps/api is built on: the file-based router loader, the hook runtime other capabilities extend it through, SSE encoding, and the gen-openapi command.

The workflows capability's toolkit: the SDK execution boundary the app imports (`client`).

The Mistral Apps gateway seam: the caller token the gateway puts on each request, the middleware that catches it, and the host wiring that makes it the credential a caller's Mistral API calls spend.

Telemetry dependencies for the Mistral Apps Observability capability.

Guided, event-based machine learning workflows with recorded provenance

Discover, verify and wire local MLX models on Apple Silicon

Python interface to manage MMIF files.

Tool to manage MMIF files.

模联 ModLink 的 Agent 工具包——把平台模型封装为 CLI 与 MCP 工具，供 AI Agent 调用

An MCP server for AI agents to execute shell commands, run Python code, manage files, and search codebases.

Sandboxed Python code execution tool for Haystack Agents, powered by Pydantic Monty

Placeholder package for MouseCat AI.

MPPI agent SDK: typed payment interfaces and exact primitives

Background denoise MP2RAGE UNI images (MPRAGEising) whilst either removing or reintroducing the bias field - Powered by AFNI

沐璃：事件驱动的本地数字生命与私人多 agent 助手

Multi-agent teams for real work: run teams of coding agents and measure them against solo agents

MA-Trace: causal tracing, coordination SLOs and deterministic replay for multi-agent LLM systems (multi-agent observability on OpenTelemetry).

Run several Claude Code accounts side by side: separate CLAUDE_CONFIG_DIR directories, launchers, proxies, environment variables and arguments.

Local-first, GitHub-native multi-agent development orchestration runtime

Core Mvge agent loop, invocation types, state management, and spell execution

Profile-driven async LLM adapter for OpenAI, Anthropic, Gemini and Ollama.

A high-throughput and memory-efficient inference and serving engine for LLMs

Run your Nagent agents from Python: a thin client over the Nagent REST API.

A local programming and testing agent with Web and terminal interfaces

Agent Control Center (devops section): sessions, worktrees, tasks and the Agent Monitor (runs, hooks, verified lands) — one view, then a controller.

Revision-aware state transition utilities for Python

HTTP host adapter for Necoherence

Memanto long-term memory backend for NVIDIA NeMo Agent Toolkit

Task-scoped Tenuo authorization for NVIDIA NeMo Agent Toolkit

Neo — AI coding agent harness with adaptive runtime and persistent memory

User-owned Ollama servers in interactive NERSC allocations

Agent de deploiement de configuration reseau piloté par Visio, KeePass et inventaire recon

Serveur MCP standalone pour netcfg-agent : expose inventaire Visio, preview, topologie, terminal SSH live en tools MCP consommables par Claude Desktop / Gemini CLI / Roo Code

Local-first exporter for AI agent conversations (Codex, Claude Code, Copilot, Cline, Cursor, Gemini CLI, OpenCode and more) to readable Markdown, HTML and PDF, in Spanish or English.

Agent-to-agent messages, plain text, image transfer, and optional encryption

Client, command line and MCP server for Nexus, the network reserved for AI agents: verifiable identity, reputation, other agents to work with.

Background Windows desktop control for Claude: an MCP server that sees and acts without taking the user's mouse, keyboard or foreground

An MCP which adds terminal capabilities to an agent.

Thin evidence chain across policy, sealed effect, witness, and CI regression.

OpenAI structured-output provider for the nl2data-core model provider boundary.

Convert text into compact logical form for token-efficient RAG

Measure an LLM judge's retest variance before you trust its deltas.

Autonomous, Local-First AI Operating System — MCP hub, hybrid RAG, neuro-symbolic governance, AMI cognitive stack

A bounded multi-provider LLM agent plugin for NoneBot2

Interactive CLI to run Ollama LLMs on Kaggle/Colab GPUs: GPU detection, fit and tokens/sec estimates, library search, public tunnel.

llama.cpp speech recognition adapter for notepipe

A swarm of agents for security purposes: attackers and defenders play 'war games' in order to better protect the victim agent

A library designed to calculate the average time between Git commits.

Bucket List: lightweight search for S3. One command sweeps every bucket in an AWS account into a single offline HTML file with drill-down, storage-class cost estimates, largest files, and instant search.

Batteries-included filesystem disks for Nyxa — local default, optional S3

MCP server for inspecting and editing Word, PowerPoint and Excel files, with no .NET install

Web research and extraction toolkit with MCP and optional autonomous LLM agents

Smarter self-hosted AI assistant for multiple users and agents, built on oi-harness

Turn a folder of files into a conformant OKF v0.2 knowledge bundle

Shared library for LLM calls at MIT Open Learning, with Opik tracing, prompt management, and evaluation built in

Agentic components for life insurance pricing, built on olivetree tools.

Python SDK for Ollama's Decision API. Convert text into structured, typed responses without prose generation using an elegant operator-based DSL.

A response generator run with Ollama and ChromaDb.

Centralized hub to manage and distribute skills, rules, and subagents across multiple AI coding assistants

MCP server engine and indexing library for OneTick LLM assistants — semantic document search and reference-data tools; configured and launched by a wrapper package (e.g. onetick-mcp).

The Open-Source Payment Infrastructure & Financial Firewall for Autonomous AI Agents

ACGS rule-based tool-call governance for OpenAI Agents SDK function tools, via tool guardrails and approvals

OpenAI Agents SDK function tools for AgentSearch: free live web search, plus pay-per-call extract and JS render

ContextFetch web search and page reading tools for the OpenAI Agents SDK

Geniffy for the OpenAI Agents SDK: a memory of each of your users, for any agent. Memory in the instructions, and tools.

Drop-in run() replacement and sandbox tools that give openai-agents agents an isolated microsandbox workspace.

OpenAI Agents SDK integration for Recall, long-term memory for AI agents: a session backed by Recall, memory tools and instructions.

Runtime Cloud sandboxes for the OpenAI Agents SDK: run a SandboxAgent in a Firecracker microVM

OpenAI extensions for MCP Python servers.

Translate via OpenAI ChatGPT Translate with requests, no login or API key

LLM dataset preparation, pedagogical semantic chunking, and RAG ingestion from OpenStax textbooks

Model Context Protocol server exposing openstax-llm pedagogical textbook chunking

Typed LLM steps and agents on the operonx workflow engine

Install Claude Code delivery and code-review skills with focused custom agents.

SQLite storage backend plugin for the Orchid AI framework

Enterprise reverse proxy and firewall middleware for Model Context Protocol (MCP) JSON-RPC tool calls

Deterministic Zero-Trust Security Sandbox & Cryptographic Audit DAG for Autonomous AI Agents in CI/CD

An integration between the Otari LLM gateway and Haystack

Local-first personal agent runtime.

Move AI conversations between Claude Code, Codex, ChatGPT, Claude and tavya, and resume them natively

Local personal assistant for terminal, voice, and Telegram, with memory that stays on your machine.

Modular, model-agnostic AI coding agent runtime

Python SDK for AgentRun: create agents, run them, and collect results

Signing, KYA, and MCP envelope primitives for building a Paygent wallet agent

An opencode-style AI coding agent CLI/TUI for Python, with a Python discovery tool and an OS/software toolbox.

Simple, minimalistic AI-Agent for Linux that runs on almost every device

A character for your group chats that knows when to stay quiet, and learns from being corrected.

Python SDK for Personal Agent Protocol draft 0.3 (2026-10-26) and its Operations extension v1

Pi coding agent as an Agents Anywhere runtime (connector adapter)

Python client for Pink Agentic AI Payments: the approval layer between AI agents and company money (sandbox).