Python agents

Python support library for the Agent Approval Interchange Specification

Reference emitter for the agent-audit OpenTelemetry semantic convention: proposed -> decided -> executed.

Local control plane for terminal AI agents: run them, message them, coordinate them through GitHub Issues, reach them from Telegram.

LLM agent execution tracer with failure attribution

Static, pre-deployment analysis of what an agentic system can reach in an AWS account from untrusted model input.

Quality gates for agent-built code: an anti-simulation tripwire, an AWS-account tripwire, and an eval harness with confidence intervals and significance testing.

Archive local AI chat histories to S3, freeing up disk space while keeping conversations searchable

자율 에이전트 및 데이터 파이프라인을 위한 경량 설정·로깅·도구 프레임워크 (Lightweight configuration, logging, and tooling framework for autonomous agents and data pipelines)

Deterministic lint and regression gate for AGENTS.md, Claude, Cursor, Copilot, and Gemini instructions.

Reproducible testing, benchmarking, and regression testing for Agent Skills.

Definitions for agent security tools: public rule sets and risk corpora, scored against outside benchmarks, watched for changes, and preserved after the source disappears.

Official Python SDK for the Agent Enrollment Protocol

Intelligent, safety-first, cross-platform file organizer for Windows, macOS, Linux, AI Agent Skills, and FastMCP.

Encrypted, capability-scoped, versioned Markdown file-tree memory for MCP agents

MemorySync for Microsoft Agent Framework: a ContextProvider with budgeted instruction-layer recall, per-run identity, once-per-turn duplicate-proof capture, and fail-open everything.

Outbound change control for AI agents — gate shell, file-write and HTTP side effects before they happen

Artifact-driven development harness for coding agents

Ahp public package coordinate scaffold

Ahp public package coordinate scaffold

Governed project memory for AI coding agents across sessions and tools

模型协议残留处理：识别漏进正文的协议头、孤儿 JSON 尾、思考标记。纯标准库。

A local-first, auditable job runner for AI-agent automation

Ultra-low latency (<10ms) deterministic security, prompt injection, secret leak, dangerous AST, and factual hallucination inspection micro-oracle for autonomous agents on Polygon, Base, and Arbitrum.

An agent that rewrites its own system prompt from execution feedback

Policy-enforced self-edit gateway for coding 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

Workspace Knowledge Protocol — progressive disclosure knowledge index for agent frameworks

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.

Reference implementation for the Agentic Knowledge Web.

An open-source, stateful engine for evidence-backed investment thesis monitoring.

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.

Exactly-once execution for AI agents — Python SDK for AgentRaaS

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.

Deterministic Android Engineering for the AI Era: Turn Any AI Assistant into an Uncompromising Senior Android Engineering Team.

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 persistence, and session-scoped clear.