Python agents

Zero-Configuration RAG Framework and Embeddable SDK for Python

Themed, non-repeating nicknames for Claude Code subagents — a userspace port of Codex's nickname_candidates

Local-first proof recorder for NativeLink-backed Bazel validation runs.

A self-improving agent inspired by Hermes Agent.

ChatGPT-5.4 Nano 中转服务 SDK - 每天免费 1.0K tokens，国内开箱即用

Keenable web search integration for NVIDIA NeMo Agent Toolkit (keyless by default)

Claude adapter for NeMo Fabric

LangChain Deep Agents adapter for NeMo Fabric

All-in-one RAG framework for Nepali Documents.

Local tool-calling agent engine: a model-agnostic loop over local LLMs (the Revenant harness).

Ness Agent is an experimental, hackable agent harness.

Kestrel: a local-first, memory-native AI engineering agent runtime.

Neutral LLM gateway: typed contracts, provider adapters and explicit retry, fallback, usage and cost accounting.

The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere

A next-generation AI agent framework.

NextPy AI Agent - Intelligent coding assistant for NextPy framework

CI-integrated evaluation harness for LLM agents

An AI-powered PowerShell assistant that converts natural language into PowerShell commands using Gemini and LangChain.

Official Python SDK + CLI for AgentOS

Framework adapters (CrewAI, LangGraph) for the Nornyx nornyx.agentic authorization SPI.

NucliaDB Agentic API for Hyperforge

AI-powered Gmail follow-up CLI agent

Official typed Python client for the NullMail temporary email Pro API

Reusable AI agent framework for building domain-specific assistants with tool use

Agent 观测 SDK：模块四段（输入/结构/流程/输出）申报 + LangChain 自动采集 + HTTP 上报

Archive AI coding-agent sessions (Claude Code, Codex, Gemini, Cline, OpenCode, Hermes) as index-safe Markdown notes in an Obsidian vault.

Average purchase and sale prices computed from invoices

This module allows to base replenishments quantities (on stock locations) on average daily sales

MCP bridge for OpenGraphMemory

MCP server that lets any agent query a remote oG-Memory knowledge base with just OGMEM_API_URL + OGMEM_API_TOKEN

Repository-owned knowledge maintenance for coding agents

SQLite-backed MCP event bus and control surface for heterogeneous agent orchestration.

Opinionated SRE ops for AgentBus: edge-triggered health watchdog and SREWatchdogAgent.

LangGraph and LangChain tools, retriever, and navigator for OKF (Open Knowledge Format) Markdown bundles

Meta-package: installs the full mitodl agent-kit toolkit (agent-config-kit's agent-kit CLI + witan + witan-code)

A local multi-agent code reviewer

A local-first personal agent with persistent conversations, memory, and a searchable knowledge base.

Omen: agentic time series analysis, forecasting, backtesting, deployment, and monitoring tools, exposed as FastMCP servers

omllm

A unified Python interface and API server for running local Large Language Models.

Persistent, branch-aware, git-anchored memory & context layer for coding agents.

Local OmniCrawl agent with TUI, tools, MCP and NPM Hook plugins

79team 运维与实施控制 (OPC) 声明式任务流引擎与安全网闸

Let teammates call your local agent or automation directly over the LAN.

Claude Managed Agents-shaped control plane backed by the OpenAI Agents SDK.

Local agent bridge for governed OpenAdapt workflows, attended actions, MCP, and Agent Skills

Agent identity & governance control plane: policy-gated, credential-brokered, cryptographically audited tool execution for autonomous agents.

Open-source CLI framework for evaluating RAG systems and AI Agents

Python SDK for the Open Agent Specification (OAS) — decentralized identity for autonomous entities

OpenAgent SDK — identity, authentication, and Agent Capability Token verification for autonomous agents.

OpenAI Agents SDK tools and a mandatory pre-execution gate for RelayShield's MCP registry risk and prompt-injection breach checks.

Normalize OpenAI-compatible API failures, plan conservative retries, redact logs, and inspect SSE streams

OpenAI v1 API-compatible HTTP service backed by HuggingFace Transformers

A self-metering guardrail that counts and caps your OpenAI token usage against a daily (UTC) cap.

A pure-stdlib hybrid Code-as-Action scientific research agent.

A vendor-neutral FinOps and measurement toolkit for AI usage, cost, efficiency, and business outcomes.

Audit any OpenAPI spec for AI-agent and MCP readiness, and generate an MCP server scaffold.

Convert OpenAPI specifications to Agent Skills format

OpenCAD AI agent — natural-language modelling on top of the OpenCAD core

Hardware-aware scheduler sidecar for OpenClaw

Open-source CLI for turning long videos into shorts, long-form candidates, subtitles, thumbnails, and review packets.

Install agent tool packages into global or project OpenCode configurations

Integration of Enterprise Content Management (ECM) systems with Haystack through toolsets, fetchers, and retrievers

Lightweight LLM-as-judge evaluation CLI — score model outputs on 5 dimensions and compare runs (OpenAI / OpenRouter / Ollama)

Guard a custom LangGraph agent with the OpenGuardrails (OGR) protocol — a drop-in ToolNode at the agent-hook altitude, with native LangGraph interrupt() as the human-confirm gate.

OpenLake high performance KV cache client and server for vLLM.

OpenMarket / AgentBazaar tools for Microsoft AutoGen / AG2

OpenMarket / AgentBazaar tools for CrewAI agents

Python port of @openrouter/agent: OpenRouter tool orchestration, streaming, state, and format compatibility.

OpenTelemetry Anthropic instrumentation

OpenTelemetry Official Langchain instrumentation

OpenTelemetry Official OpenAI instrumentation

OpenTelemetry Official OpenAI Agents instrumentation

Agentic system optimization: coding agents reason over parameter meaning and trial history.

Meta-factory over all wrapped optio agent engines: create_task dispatched by a tagged TaskConfig union.

OpenAI Agents SDK tools for the OptionsAhoy equity-compensation calculators.

Pydantic AI tools for the OptionsAhoy equity-compensation calculators.

Консольный клиент к OpenRouter API для Termux и Linux

Orqis SDK - one line to stream AI agent traces to Orqis self-healing ops

Ory Agent Security for the Microsoft Agent Framework — per-tool authorization, activity logging, and identity propagation via function middleware. Built on ory-argus.

Ory Agent Security for CrewAI — per-tool authorization, activity logging, and identity propagation by wrapping tools. Built on ory-argus.

Ory Agent Security for LangChain / LangGraph — per-tool authorization, activity logging, and identity propagation via an AgentMiddleware. Built on ory-argus.

Ory Agent Security for LlamaIndex — per-tool authorization, activity logging, and identity propagation by wrapping FunctionTools. Built on ory-argus.

Ory Agent Security for the OpenAI Agents SDK — per-tool authorization, activity logging, and identity propagation via a tool-input guardrail. Built on ory-argus.

Ory Agent Security for Pydantic AI — per-tool authorization, activity logging, and identity propagation via a WrapperToolset. Built on ory-argus.

Deploy local LLMs behind your own managed API server - vLLM or llama.cpp in isolated environments, with API keys, workspaces, and usage tracking.

LangChain and LangGraph integration for the Outsail Context Intelligence Platform

Claude Code, overclocked — multi-account hot-swap, context-threshold handoff, instrumented statusline, and model routing for multi-agent workflows

Bidirectional LaTeX sync for Overleaf — push, pull, and conflict resolution via git worktree

Agentic AI framework untuk audit keamanan kode Python berbasis OWASP Top 10 (2025).

Official Python SDK for the Paive patent intelligence report API

Shared runtime and agent skills for Frowang paper research workflows.

Universal Payment & Monetization Engine for AI Agents — HTTP 402, multi-rail wallets, budget guardrails, escrow, and @paywall for FastAPI/MCP.

LangChain tool for PayPack: AI Agent autonomous payments (HTTP 402, x402, AP2)

SDK de integração dos agentes da Paytime com o Agentes Hub

Unified Agent Core — declarative agent manifests, pluggable registries, and interfaces for the AgentForge harness.

PeerPedia Storage GitDB — git + SQLite implementation of ArticleStorage

Evidence-based AI physical preparation platform — backend

A points ledger for AI agents, delivered as a signed macOS MCP server app.