Python agents

A document-to-agent-context compiler.

A multi agent communication toolkit.

Modular node architecture for LangGraph agents

Coming soon...

Coming soon...

Budget evaluator for agent-control -- cumulative LLM cost and token tracking

Cisco AI Defense evaluator for agent-control

Galileo evaluators (Luna, Decision Models, LLM-as-judge) for agent-control

Builtin evaluators for agent-control

A centralized hub for multi-agent code creation, enhancement, and deployment

Datagusto Agent Control Layer

Shared data models for Agent Control server and SDK

Layer 3: The Framework - A governance and management layer for autonomous AI agents

Coming soon...

Python SDK for Agent Control - protect your AI agents with controls

Server for Agent Control - manage and evaluate controls for AI agents

Score how similar N agent outputs are — exact match, Jaccard token overlap, divergence point, composite 0-1 score. Stdlib-only.

Durable parallel conversations between LangChain agents.

Evidence-first, artifact-driven bug triage workflow for CLI agents

Slack for AI agents — rooms, messaging and context sharing for multi-agent coordination

Tool-agnostic multi-agent workflow coordinator. Orchestrate AI coding agents through a structured handoff protocol.

A multi-agent orchestration system for managing AI coding agents (Claude and Gemini) in parallel git worktrees with a real-time web dashboard.

Core framework for multi-agent systems

A clean Python runtime for multi-provider LLM apps and agent workflows

Common building blocks for creating AI agents.

Thin CLI + MCP client for Agent-CoreX — execute any task with a single query

A multi-agent orchestration system for managing AI coding agents (Claude and Gemini) in parallel git worktrees with a real-time web dashboard.

Middleware proxy for AI agent request attribution and compliance audit trails

Budget limits and cost guardrails for AI agent frameworks (CrewAI, AutoGen, LangGraph)

Config-driven multi-agent debate council — add a reliability layer to any LLM pipeline

Web portal for monitoring and interacting with AI agent sessions

Framework-agnostic coverage testing and observability tool for LLM Agents.

Database Copy-On-Write for AI agent workspace isolation

Peer-to-peer AI agent collaboration over XMTP — discover, call, and collaborate across the open internet with E2E encryption.

Intelligent context management for AI agents with cost optimization

Agent Cultivation -- Structured growth and training paths for AI Agents.

Data model and renderer for agent workspace screens.

Unified multi-source content CLI for discovery, sync, local query, and explicit interaction.

Agent data residency + GDPR Chapter V transfer-basis runtime guard. Programmatically answer 'where does this data live?' for agent-to-agent transfers. Adequacy decisions, SCCs, BCRs, EU AI Act Article 10.

Connect agents to data

Agent 训练数据的校验、转换与批处理工具。

Diagnose why your AI agent failed. Root cause analysis + fix suggestions.

Agent Debugger for LangChain/LangGraph

A placeholder package for agent-deck

Local-first Agent batch evaluation and failure analysis CLI

Translate canonical coding-agent definitions into platform-native agent artifacts.

Universal cheap-subagent CLI — route low-reasoning tasks from Claude Code / Codex to Ollama, LM Studio, OpenRouter, Anthropic Haiku, and other backends.

Agent Delegation MCP server. Tools: create task, delegate task, get task status. Built by MEOK AI Labs.

Agent-agnostic AI CLI delegation with federated model failover

MCP server for Agent Deploy — deploy and manage apps from any AI client

AI Toolkit - CLI and SDK for agent debugging and workflow visualization

Agent-operated developer-experience CLI — deterministic per-backend markdown briefings for autonomous agents.

AI Agent Development Workflow CLI - Universal version

Chrome DevTools for AI Agents - Real-time debugging, pause, inspect, and step through your AI agent execution

Agent Reliability Observatory — a behavioral taxonomy and annotation framework for analyzing why coding agents succeed or fail.

Python SDK for the Agent-DID Specification (RFC-001) — create, sign, resolve, verify and revoke Agent-DIDs

Python SDK for Agent Diff - test AI agents and train models against replicas of services

A microframework for creating simple AI agents.

Agent-to-Agent service directory — discover, register and rate AI agent services

Renamed to agentdiscover. This package is a redirect stub.

信息获取与新闻聚合器

MCP server that lets Claude Code agents delegate tasks to agents in other project directories

A lightweight agentic mesh for orchestrating AI agents.

Security, Governance and Audit framework for AI Agents

Interactive document sessions with AI agents

A command-line tool to auto-generate and update file-level docstrings summarizing classes and functions. Useful for maintaining a high-level overview of your files, especially in projects with code generated or modified by AI assistants.

Python SDK for agent-doctor — instrument AI agents with one init() call

MCP server giving AI agents eyes and hands inside Android devices via ADB

AI Coding Assistant Session Export Tool

ASCII art office animation plugin for Claude Code — watch your AI agents work in a tmux pane

Agent cost control, energy budget management, and token tracking

Agent Enforcer: A modular code quality checking tool

Command-line interface for managing Google Cloud Vertex AI Agent Engine deployments

Agent Environment Protocol - 基于文件系统的 Agent 管理协议

Environmental Abstraction for General Agent.

Agentic Context Engineering (ACE) middleware for LangChain — self-improving playbooks from the ICLR 2026 paper by Zhang et al.

Know what an AI task will cost before you run it

Agent evaluation toolkit

Open-source multi-turn AI agent simulation and evaluation

A local-first, lightweight harness for AI agent evaluations

Lightweight agent evaluation framework — zero dependencies, local-first, framework-agnostic

Deterministic evaluation tools for AI coding agents, exposed as an MCP server.

Python RPC client, official optimizer bridge, and DSPy metric adapter for @tangle-network/agent-eval.

A generative AI-powered framework for testing virtual agents.

Production-ready evaluation framework for AI agents — 58 metrics (25 native + 33 Harness Config) across 7 evaluation gates: goal achievement, behavioral integrity, reliability, performance, security, multi-agent coordination, and observability

Typed SSE event protocol for AI agents — token, tool_use, thinking, progress, done

Evidence capture primitives for autonomous agent systems.

A comprehensive toolkit for evolving and tracking AI agents

Tool to simulate multi-agent interactions in competitive environments

A lightweight execution guard for AI agents. Decide ALLOW / HOLD / DENY before your agent performs real actions.

A panel of experts that will solve problems and discuss topics

Native accessibility-tree computer use for AI agents across desktop applications and browsers

Core library for building AI agents with pluggable models and channels

FailSafe governance adapter for Microsoft Agent Governance Toolkit

Diagnose why your LLM agent failed. Deterministic causal analysis with fix generation.

DuckDB multi-org agent swarm with Spec Engine, 175+ SQL macros, meta-learning, MCP Apps, and smart extensions

CLI for installing AGENTS.md, .agents rules, AI coding workflows, and client adapters into software projects.

Quality signals for MCP tools — agents report results, building a community-driven quality database

CLI tool for fetching AGENTS.md files from GitHub