Python agents

AgentAvow (formerly agentgraph-pydantic) trust verification middleware for PydanticAI agents

Python SDK and CLI for the AgentAvow trust and identity platform (formerly agentgraph-sdk)

MCP server for AgentAvow (formerly agentgraph-trust) — trust verification, security scanning, and identity lookup for AI agents

Run your own autonomous AI worker on AgentBounty

Policy-sandboxed runtime for AI agent processes: enforce a policy file, capture a tamper-evident trace, deterministically replay any run.

Agent-neutral policy-engineering framework

Python SDK and read-only MCP server for AgentClose

CLI for initializing, validating, and managing AgentConv-compatible repository structures.

AI-agent read coverage for source files, with LCOV and gcov-compatible reports.

Agente conversacional para gestionar eventos del calendario usando LLM local. Ejecuta la operacion correspondiente en el archivo .ics del calendario / Conversational agent for managing calendar events using local LLM. Executes the corresponding operation on the calendar ICS file.

Name reservation for the agentfenster Windows app - the application is distributed via agentfenster.com.

Launcher for the agentfenster MCP server - Windows GUI automation on a hidden second desktop.

AI-assisted pipeline that converts RDF Turtle (.ttl) knowledge graphs into a ChromaDB vector database

Shared invoke-boundary core for agent-governance-demo: host adapters, entitlement/policy resolution, the governance envelope, and the registry Postgres schema. Published to PyPI via OIDC Trusted Publishing (.github/workflows/publish.yml) and installed into registry-api/workflows images.

Discord connector for AgentGraph

Google Docs, Sheets, Gmail, and Drive connectors for AgentGraph

RSS and Atom connector for AgentGraph

Slack connector for AgentGraph

Generic web page connector for AgentGraph

A local-first CLI and MCP server that turns selected digital sources into a searchable graph for the AI agent you already use.

Detect loops and wasted calls in AI agents

Clean messy CSVs with an agentic workflow: an LLM decides the steps, tested code does the work.

AI Developer Governance & Codebase Evaluator — A GraphRAG-powered multi-agent system featuring autonomous code evaluation, red-team testing, and dynamic LLM-narrated architectural documentation.

Type-safe LLM-powered functions. Write intelligent functions with decorators, not agents.

A Model Context Protocol (MCP) server exposing Gmail operations for AI agents

Skills Manager: scan, install, update, and analyze AI agent skills safely across Claude, Cursor, Codex, and OpenCode.

Decision infrastructure for autonomous AI agents: evaluates a proposed blockchain action intent and returns an explainable ALLOW/WARN/BLOCK decision before execution, signed as a verifiable OAA token.

An MCP which adds terminal capabilities to an agent.

An MCP which adds terminal capabilities to an agent.

Project lifecycle CLI for agentive projects — task status flow, environment doctor, evaluator provisioning

Financial governance SDK for AI agents

A Hamachi server for agents: start a hub, get an address, agents join and work together

AgentMemory 微服务的 Python 客户端 SDK

面向 LangChain / LangGraph 开发者的 AI Agent 三层记忆管理微服务

Local-first flight recorder for AI coding agents: hash-chained audit trail, MITRE-mapped sequence detection, DLP

A Python-native runtime and workspace for observable, human-governed AI applications.

Python SDK for Agentomy AI Governance Platform

Observability for Claude Code subagents. Parses session transcripts, surfaces what agents actually did, and flags the failure patterns.

Native, in-process reinforcement learning SDK for AI agents — in-memory and local-file storage by default.

Compile ordered Markdown policy modules into a deterministic, verifiable AGENTS.md.

Report when the files your agent trusts — CLAUDE.md, AGENTS.md — no longer match the repo.

Deterministic security scanner for AI agent skills + Trusted Distribution CLI. Local, zero-dependency, executes nothing. Facts, not verdicts.

Blameless postmortems for your coding agent. Auto-memory remembers — it doesn't learn.

One source of truth for your AI agent instructions. Generate and validate AGENTS.md, CLAUDE.md, .cursorrules, Copilot, Gemini and Windsurf instruction files from a single file.

Move a coding-agent session between tools without re-explaining your project.

Approve or deny your AI coding agent's risky commands from your phone, with an audit trail. Works with Claude Code and OpenAI Codex.

Pytest-style behavioral testing for AI agent pipelines

Benchmark and compare AI agents with deterministic, reproducible tests.

AgentYard SDK — register, discover, and manage A2A agents

Model-independent orchestration of external coding-agent runtimes.

AI Dynamo LLM serving client — OpenAI-compatible inference client with multimodal support

AIPost.email tools for CrewAI — structured AI agent messaging with Ed25519 identities

Amazon product search volume as a ready-made tool for LangChain, CrewAI, AutoGen, and any tool-calling AI agent. Search volume, growth signals, and live best sellers. No Amazon API key. Powered by trendsmcp.ai

App download trends as a ready-made tool for LangChain, CrewAI, AutoGen, and any tool-calling AI agent. Weekly series, growth percentages, and live charts. Powered by trendsmcp.ai

Arabic-First PDF Extraction, RTL Normalization & Table Chunking Engine for RAG Systems.

Self-hosted AI voice agent for Asterisk. Streaming speech-to-text to LLM to text-to-speech over AudioSocket, with barge-in and correct 20 ms frame pacing.

Tool-driven autonomous software engineering assistant

Microsoft AutoGen tools to charge per agent task via U.CASH (HTTP-402). Non-custodial.

AI-powered Python unit test generation agent with ReAct architecture

Bifrost path-tunnel agent — connect a local Mac app to Bifrost

OpenAI provider for BindAI

Agentic RAG for your browser bookmarks — local-first, BYOM, privacy-focused.

Secure local execution agent for Brinqz Cloud

A deterministic Python library for parsing, normalizing, and validating brokerage statements across brokers and statement formats.

Python SDK for Browser Agent

Gemini model capability for bysulf

SQLite persistence adapter for bysulf runs

Caesar: autonomous AI research agent with graph-based deep web exploration and adversarial answer synthesis.

Standardized compatibility checker for local Ollama model tool-calling support

自主进化的 AI Agent 框架 - 人格数据主权 + 情感底色 + 元反射性学习 + 自主思考循环，零 LangGraph 依赖

An MCP which adds terminal capabilities to an agent.

CrewAI memory backed by Citadel: encrypted at rest, with deletes that destroy the key

LangGraph store backed by Citadel: encrypted at rest, semantic search, cryptographic deletes

OpenAI-compatible API server for the Claude Code CLI — streaming, tools, vision, and live session reuse.

Claude Code's projects/<slug>/ path encoding, as a function

Interactive TUI for debugging token usage of Claude Code sessions

Local privacy and proxy consistency audit for Claude Code and agent skills

Onion-architected, autonomous Claude Code session runner and full Anthropic SDK CLI — never blocks on a human, distinguishes rate limits from exhausted credits, and resumes safely across usage windows.

Hierarchical AI-generated index over a claudesync export of your claude.ai conversations.

Standalone Cognee memory provider plugin for Hermes Agent.

Control-first coverage and blind-spot analysis over an evidence corpus, with a Statement of Applicability.

Local multi-client RAG server over the Model Context Protocol

Automated Chain-of-Thought Red Teaming Agent

CLI AI coding agent: ReAct tools, hybrid RAG, multi-provider LLMs

Full-lazy single-model CRC-LNM research-assistance MCP for ModelScope STDIO

CrewAI tool for decision_binding_ref — content-addressed binding between an action and the decision that authorized it

CrewAI integration for Lumify Sports Intelligence — connect the hosted Lumify MCP (schedules, live scores, odds, betting splits, explainable AI bet confidence) to any CrewAI agent in one call.

TollWarden payment security for CrewAI agents: scan x402 payments before settling, auto-tag provenance for prompt-injection detection via a tool-call hook, and guard payment tools so blocked payments can never execute.

Extract and summarize Claude Code sessions into daily reports

Deterministic Adversarial Simulation (DAS-LLM) Framework for LLM Security Invariants

LiteLLM custom provider for Databricks Model Serving with live fuzzy model resolution

AI coding agent harness — chat-session based, GitHub-native, offline-first

LLM-facing DEX/APK analyzer — pybind11 wrapper around DexKit Core with an embedded DAD-aligned Java decompiler, MCP server, and FastAPI/SSE backend

Make Django sites first-class citizens of the agentic web: llms.txt, Schema.org/JSON-LD, agent discovery, WebMCP tools, agentic commerce/booking and SDF — per-site opt-in.

Django app for Cursor Cloud Agents

A Python application toolkit for GPU-native data tools.

Dynatrace OneAgent Python code module for Azure Functions

EmbodiaRobotAgent — embeddable end-to-end conversational robot SDK

Terminal-based AI coding agent with reusable skills, personas, and a Web UI

An MCP server that lets AI agents read real, messy Excel files: multiple sheets, title rows, merged cells.