Python agents

Agent Token Manager (agent-atm) - A lightweight, privacy-first LLM token usage metering & quota capping SDK.

Agent Attention - Pytorch

Python SDK for the Agent Attribution Protocol (AAP) — AI agent affiliate attribution

Static security analyzer for AI agents — prompt injection, tool input validation, MCP config auditing, secret detection. 66 rules mapped to OWASP Agentic Top 10.

Security scanner for MCP-connected AI agent pipelines

Hash-chained HMAC-signed audit log MCP for A2A (agent-to-agent) calls. Every tool-call, agent-handoff, decision gets a tamper-evident signed record. EU AI Act Art 12 automatic logs, DORA Art 17 ICT incident logs, ISO 42001 clause 9 monitoring — auditor-ready end-of-day attestations. By MEOK AI Labs.

Tamper-proof compliance audit trail for AI agents. EU AI Act Article 12 + SOC 2 ready.

Immutable audit logging for AI agents — hash-chained event log, integrity verification, EU AI Act compliance

Debug AI agent failures with minimal-config execution traces

A distributed, scalable filesystem backend for deep AI agents, backed by blob storage

Agent BDI framework

Evaluation harness for real headless CLI agents - reproducible multi-turn scenarios, rule + LLM scoring, cross-agent comparison

Reserved - autonomous job application agent. Real release coming soon.

A Python SDK for MCP tool integration with LLM providers

Declarative AI agent orchestration with runtime guarantees: YAML blueprints compiled to LangGraph, with lint, deterministic tests and CI gates

Open security scanner and self-hosted control plane for AI, MCP, and cloud infrastructure.

Failure memory and epistemic guardrails for AI agents

Agent Brain CLI - Command-line interface for managing AI agent memory and knowledge retrieval

Agent Brain RAG - Intelligent document indexing and semantic search server that gives AI agents long-term memory

Chaos Monkey for AI agents

CLI tool for maintaining a shared local registry of reusable GitHub repos and scaffolding new coding-agent projects.

Python wrapper for agent-browser CLI — browser automation for AI agents, no npm required

Add your description here

Budget-limited LLM API client wrapper to prevent runaway AI agent costs

The agent-builder package to develop LLM based models.

MCP server that agents built with the Agent Builder SDK use at runtime to communicate with AWS Transform

Python SDK for Agent Builder Gateway - 用于 AI 构建的程序调用预制件

MCP server for building, deploying, and managing agents on AWS Transform

Python MCP client provided by the AWS Transform team

A professional-grade AI utility for automated data synchronization and backend management.

Base agent SDK for building orchestrator and subagents on AWS Transform

Type stubs for boto3 TransformAgenticService client

Local SQLite-backed MCP bus for peer coding agents

A Zero Trust Cryptographic Certificate Authority SDK for Autonomous AI Agents.

Python SDK for Agent Café — the agent-to-agent marketplace

Agent-first CAN control MCP server

Scan your agentic codebase for unguarded tool calls with real-world side effects

A virtual currency system where AI agents trade capabilities in a marketplace

Carbon emissions tracking for LLM agent frameworks

AI coding agent definition manager — fetch, install, and cast across tools

Scoped Event System for agent-era browser automation

Persistent two-tier memory for AI agents. Short-term markdown + long-term SQLite with semantic search.

LLM-solvable challenge-response authentication for AI agent APIs

Chaos Engineering for AI Agents

AgentChat facilitates the creation of AI assistant and the development of advanced multi-agent system.

Daemon that bridges chat platforms (Rocket.Chat and more) to AI agent backends (Claude, OpenCode)

Agent Chat Room MCP server - Allows multiple Claude Code agents to communicate with each other

Temporary chat rooms for AI agents to communicate in real-time

MCP server for Agent Chatroom — join 10 AI agents discussing humanity's biggest questions

Type-guided externalized state for LLM agent frameworks.

CI/CD verification pipeline for AI agent outputs — fact check, schema validation, diff verification

Content-addressed artifact manifest for AI agents (Python port of @p-vbordei/agent-cid)

A suite of AI-powered command-line tools for text correction, audio transcription, and voice assistance.

Structured LLM task runner with outcome routing via file signals

A tmux wrapper for LLMs to interact with full-screen CLI applications

Unified CLI gateway for enterprise & developer platforms — one Skill to search, install, auth and invoke 8 platforms, 159+ tools

Capability-first Codex control plane for long-running developer workflows.

Universal SDK for interacting with AI Agent CLIs (Gemini, Copilot, etc.)

Ask openai on your terminal

A Python client library for communicating with the Flask server

A Jupyter Kernel for Agent Client Protocol using MetaKernel

A Python implement of Agent Client Protocol (ACP, by Zed Industries)

A CLI-driven virtual filesystem for AI agents

A meta-level agentic workflow that creates independent, self-contained AI agent clusters

MCP server for orchestrating multi-subagent code runs with minimized context and patch-only outputs.

一个具有程序执行监控和中断功能的 AI 代码构建智能体

Lightweight semantic code search and distillation utility for AI coding agents. It solves the API knowledge gap via real-time local signature extraction and intent analysis without PyTorch. Optimized for token efficiency, it compresses codebase context into compact semantic summaries stored in a local DuckDB vector similarity index.

MCP Server for AI coding agent standards

Vendor-neutral MESI + optimistic-concurrency coordinator for multi-agent state — a stale write is denied or returned as a typed conflict, never silently applied; safety invariants model-checked in TLA+

Multi-agent colosseum framework. Prove that agents debating, researching, and red-teaming produce better answers than a single agent.

Python SDK client for AgenticTrade marketplace API

MCP Server for agent commerce — how AI agents create, compare, and track purchases

MCP server for agent commerce payments. Features create invoice, process payment, escrow funds. From MEOK AI Labs.

Version control for AI reasoning — every LLM turn gets a content-addressed, queryable commit ID

Let AI agents form companies that hire humans - Ask for Kindly Help, Ask for All Help

Spin up an AI agent company - a business run by AI agents, managed by you

Compliance middleware for AI agents. PII redaction, audit logging, consent management, and DPIA generation in 3 lines of code.

Core library to compose, validate, and run ADK agent systems from YAML.

Agent Computer

Windows desktop control and capture toolkit for AI agents.

Centralized AI agent configuration manager for Claude, Gemini, Cursor, Copilot, and Codex

Agent configuration loader and normalizer for AI/LLM applications

An SDK that enables agents to connect with each other, allowing them to perform identity authentication, end-to-end encrypted communication, automatic protocol negotiation based on LLMs, and efficient data exchange.

This is my tools package

Reliability layer for AI agent workflows: validate state, handoffs, and outcomes before agents continue.

Governance harness for decision-making systems with structured review, epistemic honesty, and retrospective calibration

CLI tool for generating CLAUDE.md/AGENTS.md from agentpack.yml

Portable system context for agents, checked into the repo.

Connect agent SDKs to context-graph components (actions-graph, skills-graph, etc.)

Integrity verification and access control for AI agent context files

Lightweight context window management for AI agents

Python package manager and MCP server for Agent Context Protocol (ACP) projects.

MCP Server that solves context window overload — smart tool pruning, relevance scoring, and budget tracking for AI agents