Python agents

Fast LLM-free search-to-context engine for AI agents

Offline-first, framework-agnostic LLM evaluation primitives.

CLI client for interacting with MAIL servers

Daemon implementation for the Multi-Agent Interface Layer (MAIL)

Types and constants for the Multi-Agent Interface Layer (MAIL) protocol

FastAPI server for the Multi-Agent Interface Layer (MAIL)

Plug-and-play RAG with native MCP support. LLM-agnostic, swappable at every level.

Integration library for Microsoft Agents with Slack

Template schema and validation for Mosaic Agent UI SDK

MothRAG: adaptive multi-arm subset routing for multi-hop retrieval-augmented generation — high-level Python API with auto-defaults.

Client library for the opengater-storage service

PACE platform plugin for vLLM CPU inference on AMD EPYC processors.

Token-efficient prompting and agentic workflows for Claude

Claude AI terminal inside Microsoft Excel using PyXLL.

sq-agents — detect installed agent CLIs + launch a preferred agent with on-screen context ('use agent to X'), for sciqnt.

Universal TUI agent for autonomous research and writing, powered by llama.cpp

Sample responses and log-probabilities from HuggingFace causal LMs

Haystack integration for sentence_transformers

Serial Alice Agent — Verifiable energy and compute attestation

A behavioral-interview simulator and coach that runs in your terminal.

One AGENTS.md, every AI coding assistant in sync. Generate CLAUDE.md, Cursor rules, GitHub Copilot instructions, Windsurf, Cline, Gemini, Aider & Zed from a single source of truth. Zero-dependency CLI for the AGENTS.md standard.

An out-of-tree vLLM plugin for Mobilint NPU runtime integration.

LangGraph drop-in adapter for Wayforth — one import, one init, execution via proxy

声明式、响应式的 Python 智能体框架，灵感来自 Apple Foundation Models 的 dynamic sessions API。

Agent Memory HTTP SDK and lightweight Agent adapter

Local read-only CLI to diagnose AGENTS.md, Claude Code, Gemini CLI, Cursor and Copilot instruction files.

Prevents untrusted data from triggering consequential actions in your agent.

kubectx-like CLI for switching Codex auth profiles

Production-grade safety guardrails for LLM agents — injection detection, PII redaction, tool governance

Developer SDK for the Agentinc agent marketplace platform

MCP server for Residual Operating Income Valuation (REOI)

Unified observability dashboard for the agent stack — metrics, audit, escalations, policy, health

AgentOrch - Autonomous Multi-Agent AI System: 30+ agents with cognitive architecture

Deterministic record/replay of LLM and tool calls for AI agents, captured into human-readable cassettes.

AutoGen (AG2) model client for JarvisClaw AI API (x402 USDC payments supported)

Microsoft Azure Programenrollment Management Client Library for Python

CLI for ChatGPT web interface — ask questions, generate images, manage conversations

CrewAI LLM integration for JarvisClaw AI API (x402 USDC payments supported)

EnvForage CLI Diagnostic Agent — inspect your ML environment

Core-tools connector for eTiKeT sync agent

Labber connector for eTiKeT sync agent

Quantify connector for eTiKeT sync agent

Lightweight provider-agnostic agentic coding backend (CLI + server) for the Euron VS Code extension.

Ferret — self-hosted outbound tunnel agent. No port forwarding, no third-party cloud.

MCP server giving AI agents tools to self-register and report real economic performance on FloweringAgents

OpenAI SDK-style Python client for ChatGPT/Codex OAuth-backed Responses workflows.

Grasp Agents Library

MCP server exposing browser automation tools via intuned-runtime

Codex (OpenAI Codex CLI) agent target plugin for kanibako

Goose agent target plugin for kanibako

Multi-agent repo boilerplate generator — scaffolds conventions, repo-namespaced skills, settings, and hooks for Claude Code, Gemini CLI, Cursor, Codex, Copilot, Google Antigravity, Cline, Aider (Ollama), opencode, and Kimi Code CLI

Universal configurable AI agent framework — production-grade, YAML-driven, open-source ready.

LangChain tools for Atomic Mail register/help/JMAP operations

LangChain integration for FunASR (SenseVoice / Paraformer / Fun-ASR-Nano) speech-to-text

LangChain integration for JarvisClaw AI API (x402 USDC payments supported)

Upstash Box sandbox integration for Deep Agents

LlamaIndex property graph store integration for SynapCores — for GraphRAG.

llama-index readers FunASR (SenseVoice / Paraformer / Fun-ASR-Nano) integration

AlgoVault ToolSpec for LlamaIndex — composite BUY/SELL/HOLD trade calls, market-regime classification, and cross-venue funding-arbitrage scans for crypto perpetual futures, backed by the AlgoVault MCP server.

LlamaIndex vector store integration for SynapCores — the AI-native SQL engine.

一个用于测试的 Mock LLM 服务器，支持 OpenAI、Anthropic 和 Responses API 格式

ESLint for your LLM prompts — catch prompt-injection risks, missing token limits, and prompt anti-patterns before you ship.

Validate llms.txt files locally, over HTTP, and in CI.

Telegram channel support for MeshAgent

Twilio SMS/MMS channel support for MeshAgent

WhatsApp Cloud API text/media channel support for MeshAgent

支持群聊/私聊消息归档、检索和 AI 图片理解总结的 NoneBot2 插件。

Drop-in LLMOps observability. Self-hosted. SQLite-default. Persona-aware. Multi-judge consensus.

PassShore Agent — AI 代码质量本地守门人 / local AI code quality gatekeeper

Independent banking event-sequence modeling toolkit inspired by arXiv:2604.08649; not affiliated with or endorsed by Revolut.

Event triggers for Pydantic AI agents

RAGfly Python SDK — RAG service for your AI agents

A local-first RAG engine that answers questions about any repository, grounded exclusively in the checked-out code with verifiable file:line citations.

Transactional safety layer for AI agent tool execution — auto-rollback via Saga pattern

Python SDK for SeaArt agent-gateway APIs

Install Super Research into a chat runtime (Hermes / OpenClaw) with `pipx run superresearch-agent connect` — an account-authed loopback bridge that drives the user's own Super Research from chat.

Wayforth tool for CrewAI agents — discover, run, and pay for 5,000+ APIs with automatic failover, in one import.

Wayforth tool for the OpenAI Agents SDK — discover, run, and pay for 5,000+ APIs with automatic failover, in one import.

Aegis policy pack: LLM Guard scanners (prompt injection, toxicity, secrets).

Bootstrap and maintain a Fumadocs-powered Project Atlas with agent skills, reusable templates, and validation.

JSON Schemas and Python contracts for AI agent memory integrity: evidence, candidate, ledger, taste, state, and ContextPack planes.

A virtual shell-over-database filesystem for AI agents: a strict, append-only memory layer with a frozen shell dialect.

Task routing layer for production AI agents — dispatch to the right agent by capability, health, and policy

AgentGuard — AI Code Security Scanner + Auto-Fixer

Lightweight Python client for the Agentic Trading Lab REST API (LLM-powered trading agents, backtests, paper trading).

Persistent memory for AI agents — store, retrieve, and recall context across sessions.

Agent-native event bus — connect agents, humans, and systems via typed events

Live observability and visualization for AI agent activity.

Collective knowledge store for AI agents — publish facts at runtime, query shared learning

AgentRelay Secure Memory Persistence and Recall integrations for AI frameworks.

AgentTrust Edge — Full Governance Platform. Policy Engine + MAD Classifier + HITL + Kill Switch.

A State-Aware Rollback and Trajectory-Replanning Framework for Autonomous LLM Agents

AgentSec-Bench: a security benchmark for LLM agents and harnesses, built on Inspect AI

Eyes for AI Agents — a machine-graded visual feedback loop coding agents consume to self-correct before claiming done.

Codex-safe Claude Code GLM-5.2 delegation wrappers.

Production-core policy scaffolder for GitHub Copilot agents in VS Code.

Production-core policy scaffolder for GitHub Copilot agents in VS Code.

Convenience CLI for installing Memanto's Claude Code integration.

Depot — 面向代码生成 Agent 的按需依赖解析系统

Agent and CLI to manage EC2 instances running self-hosted LLM inference: warm up an instance and serve an LLM, then hibernate it on idle to power ongoing inference workloads such as ADLC. Built on ec2-cli for the underlying EC2 machine lifecycle.