Python agents

Discover local Claude Code / Codex session logs and export them as OpenTelemetry GenAI-compatible traces.

A unified AI Orchestrator CLI integrating Agent Forge and Spec Kit

Agent Skill Mastery Engine: runtime-neutral WikiSkill-method skill evolution core with thin runtime adapters

Unified abstraction layer for agent SDKs (deepagents, Qcoder SDK, etc.)

Human-in-the-loop approval firewall for Python agent tool calls

RETIRED — agent-wkp has moved to a Rust binary (wkp); see the project's GitHub Releases

Detect cross-OS portability issues in AI agent workflows, skills, configs, and scripts.

Automatic LangChain Agent observability for AgentBase AgentOps

Agentbase SDK for Agentbase API projects

A firewall for AI agents: block prompt injection, guard tool calls, redact PII/secrets.

Push notifications and phone approvals for AI coding agents and scripts (ntfy, Telegram, OS fallback).

AI-native computational fluid dynamics for humans and agents.

自主任务 Agent：面向模糊长目标的多步自主执行引擎（LangGraph），零业务依赖

Agent Cooperative public package coordinate scaffold

Agent Cooperative public package coordinate scaffold

Unified observability for LLM/text, image, and video calls (Django adapter)

Notification management module (webhook, email) for Django

Unified task execution tracking for Django (Celery integration)

Agent Environment public package coordinate scaffold

Forensic reconstruction for AI agent security incidents (local-first, standards-aligned, defensive DFIR).

Reliability and audit-ready testing for LLM agents (Python bridge to the AgentEval engine).

A modular framework for coordinating specialized software agents.

Telegram bridge and MCP gateway for user-owned AI agents

Framework-neutral portability layer for AI agents, tools, and model providers.

Shared mutation feed connector and server for AgentGraph

Self-hosted Agentic Resource Discovery over local scripts, agent skills and MCP servers.

Schemas, canonical digests, and reference validator for Agentic Graph Specification 1.0

Cost-aware multi-provider LLM router with role tiers (cheap/mid/chief/audit).

Normalization layer for OpenTelemetry GenAI agent traces. Single parsing pass, framework detection, span classification with confidence scores.

Python codebase intelligence and documentation for AI agents.

Neuronto - Agentic Resource Discovery (ARD) Index. Make your API, MCP server or AI agent discoverable by AI agents. Alias for ard-publish.

Two standalone checkers and a reading API for AgenticSystemCore knowledge nodes, in pure Python, with one agsc command that hands every other verb to the Node engine.

An open-source AI agent that tests investment theses against new company disclosures.

Local verifier for agentic data handoffs: envelope, provenance, trust, authority, identity, capability, and audit checks.

Operator-approved digest-only Harness extension for Transfer Verifier.

An MCP which adds terminal action capabilities to an agent

CLI Based Agent

An MCP which adds terminal capabilities to an agent.

Agent Environment public package coordinate scaffold

Lightweight Python agent framework. Config → agents → run.

Peer review for AI agents using independent model juries and deterministic aggregation.

Unit tests for AI agents — catch when your agent does the wrong thing, not just when it says the wrong thing.

A financial clearinghouse and dynamic credit-allocation middleware for stateful, hierarchical multi-agent workflows.

Official Python SDK for the AgentMux control plane (health, invocations, management, bootstrap).

Behavioural monitoring for AI agents: runtime baselines, scope enforcement and cold-start-safe anomaly detection.

Embedded AI agent governance peer. Standalone or connected to Agentomy infrastructure.

Learn how AI agents actually work by building a real one, from a single LLM call to a full agent harness.

AgentPayments gate for Python web frameworks — charge AI agents USDC on Solana before they can access your API

Find CI agents that eat untrusted GitHub events and hold secrets

Adaptive chaos-testing for LLM agents: a live model-driven Injector that reads an agent's real trajectory and decides where to break something, instead of scripting perturbations in advance.

Agent Environment public package coordinate scaffold

Stateful simulation and fault-injection testing for AI agents that take actions through tools.

Reliability layer for AI agent actions: exactly-once tool calls (@exactly_once, LangChain and CrewAI protect_tool, MCP wrap), an MCP safety scan, a chaos tester for duplicate calls, and the AgentRaaS client for policies, approvals and audit

Pre-trade token risk scoring and honeypot detection for Base Network, paid via x402

Declarative scheduled flow runner, per-request agent loop, and job kernel for local agent services

Mint and sign agent Ed25519 keys (did:key). CLI only; no MCP.

Append-only JSONL session traces, assemble, and MCP inspect tools

The primitives layer for every coding agent — one handler API over per-agent hooks, instruction files, plugin packaging, and config.

Stop paying for out-of-order MCP tool calls. Author-side job-graph enforcement.

See the web the way an AI agent sees it — and measure where sites serve agents a different, sometimes poisoned, page.

File-based handoff protocol for AI coding agents + a PreToolUse safety guard.

Optional advisory-only AI Agent Handoff extension for Agentic Security Harness.

Evidence-first tools for validating AI agent persistence publications and probing durable state serialization

Check what an LLM is given for prompt injection: material at ingest, tool output, and the turn it answers

Runtime firewall for AI coding agents — gate every tool call, MCP call and skill against a least-privilege policy.

The agentic behaviour layer for Keystone: declarative rules, triggers and a fail-closed guard. Cython-compiled.

Approval-first, evidence-bound development harness for supported Gradle Android projects.

Unofficial local-first agent bridge for Ansys Electronics Desktop

Shared, product-neutral runtime primitives for Apodex agents

ARK Runtime SDK — attach ARK decision telemetry, cost attribution, and (experimental) constrained supervision around your existing agent.

An LLM agent that standardizes legacy biomedical metadata to adhere to CEDAR templates

In-guest Agent Protocol server that drives the Claude Agent SDK for Athena coding tasks

Local-first Git commit message generator powered by Ollama

MemorySync for Microsoft AutoGen: an async-native Memory implementation with a hard recall budget, role-aware retrieval, duplicate-proof fact capture, and session-scoped clear.

Easy data distillation of LLMs for text classification, information extraction, and open-ended tasks

Self-contained, general-purpose LLM agent for the Autourgos framework — works with any OpenAI-compatible LLM

A CLI coding agent with full observability, multi-model support, and security guardrails

The Babel that lets AI agents understand each other: a neutral layer where heterogeneous agents (callables, HTTP/OpenAPI, MCP, framework agents, LLMs) share one interface, collaborate (A2A), and get graded at each hop.

Report line coverage from lcov.info (produced by grcov or cargo-tarpaulin)

MemorySync reference architecture for AWS Bedrock agents: a memory-augmented Converse loop and a Bedrock Agents action-group Lambda — the first vendor action-group memory integration.

Official Python SDK for Blazing Agents

Agent integrations for CapSolver — framework-agnostic tool definitions + LangChain tools.

Thin HTTP client for the RAG debugging/eval platform — register an external RAG, upload datasets, run experiments, fetch results.

A first-principles evaluation framework for LLM agents based on causal invariants, state transitions, and counterfactuals.

Cryptographic runtime receipts for Microsoft AutoGen agents — signed Ed25519 audit evidence for every tool call.

Cryptographic runtime receipts for CrewAI agents — signed Ed25519 audit evidence for every tool call. CCS (Correctover Conformance Shape) L1 + behavior receipts with pre-admission guardrails.

Cryptographic runtime receipts for LangChain/LangGraph agents — signed Ed25519 audit evidence for every tool call.

Cryptographic runtime receipts for LlamaIndex agents — signed Ed25519 audit evidence for every tool call.

Cryptographic runtime receipts for OpenAI Agents SDK — signed Ed25519 audit evidence for every tool call.

Cryptographic runtime receipts for Pydantic AI agents — signed Ed25519 audit evidence for every tool call. CCS (Correctover Conformance Shape) L1 + behavior receipts.

MCP server for the OpenAI Ads Advertiser API, with retries, response budgeting and postcode-level location lookup

Unofficial ChatGPT website client for Python.

Reserved name. Cirrus Networks internal package — not distributed on PyPI.

Reserved name. Cirrus Networks internal package — not distributed on PyPI.

Save, restore and manage Claude Code sessions as workspaces. Windows Terminal native.

Show your Claude Code sessions on an iDotMatrix LED panel.

Claude Code limits and reset times in the macOS menu bar

Log in to Claude.ai without touching your inbox: magic links auto-open in the right browser via IMAP IDLE

Select OpenRouter models directly inside Claude Code