Python agents

Lightweight utilities for building AI agent harnesses

A provider-independent port for delegating work to agent harnesses

LangChain and LangGraph adapter for Agent Harness Protocol

An open benchmark for prompt injection against tool-calling agents.

Python SDK for AVEL (Agent Verification Layer) — identity/reputation verification for agent-to-agent payments

Corroboration engine for agent tool-call arguments

Deterministic JSON repair and JSON Schema validation for AI agents and software. No LLM required.

Production-ready framework for building AI agents — type-safe, observable, circuit-broken.

Unified Future AGI SDK for agent learning workflows.

See what your AI agents are actually doing. Local-first tracing and debugging for AI agents.

Message the CLI agents on your machine from your phone — every message becomes part of their memory.

Checkpoint-gated developer/reviewer loop across Claude Code, Codex, Grok, and Antigravity CLIs.

Local-first AI agent team workbench: project-scoped MCP mailboxes for existing apps and CLIs, shared context, task handoffs and human review.

Who authorized an AI agent to act, whether it stayed inside those bounds, and what it cost when it did not.

Official Python SDK for the Agent Margin Router API – one pay-per-call endpoint for web, market, on-chain, DeFi and developer data. Pay with USDC on Base via x402, or use an API key. 3 free calls per wallet.

Keep agent plugin and marketplace versions in sync.

Agent Memory Integrity (agmi): a conformance test suite that measures whether AI agent memory and checkpoint stores notice tampering

Local memory, a codebase index, and working discipline for AI coding agents. Zero dependencies, no network.

Placeholder package reserving the agent-meta-runtime name on PyPI. Real implementation tracked in docs/Agent_Meta_Runtime_Seed_Harness_Requirements_Design_v0.1.md.

A lightweight bwrap sandbox for AI agents

Autonomous behavior firewall, vendor-agnostic control plane, and permanent memory across Gemini, Claude, Codex, Copilot, Cursor, and Windsurf

Agent orchestration patterns over long-running coding agents

Run several coding agents in isolated worktrees with shared coordination.

A local IPC mesh so any AI coding agent harness (Claude Code, Codex CLI, Antigravity, pi, opencode, ...) can find, message, and reactively wake up any other.

Official workload SDK for Agent Platform. Placeholder release; the SDK ships here.

Audit LLM API routers for tool-call tampering, credential exfiltration and supply-chain risk

Client-side tool-call gate for coding agents: screens what Claude Code and Codex are about to run, and keeps a tamper-evident record of it.

Deterministic Anti-RLHF Stylometric Gate for Autonomous Agents by Nitivra

Plug any AI agent into real evaluation scoring, guardrails, and observability tracing in minutes — framework-agnostic, 100% free, no signup, never touches your API key.

Lightweight utilities for building AI agent harnesses

Hello world package for Agent RT Lite.

Reconnectable native agent workers with durable input receipts and events

Diff-scoped mutation gate for pre-commit and agent Stop hooks

Git staging as the human review surface for collaborative agent sessions

Share coding-agent sessions (Claude Code, Codex CLI, OpenCode, Gemini CLI) with your team through git.

Portable skill catalog search for AI agents — MCP server + CLI

Scan, classify and sync AI-agent skills (SKILL.md) across toolchains like OpenAI Codex, Claude Code and WorkBuddy.

Agent skills for writing and reviewing PSS (Portable Test and Stimulus) models

A lightweight CLI tool for delegating LLM tasks to expert models across multiple providers.

Build agent instructions from your project's sources.

Licensed local MCP server. Verify supplied agent spend mandates and transactions against merchant, category, currency, time and budget limits.

A dense, width-aware status line for coding agents

A conservative scanner for AI-agent skills, MCP manifests, and configurations

Deterministic Epistemic Sycophancy Gate for Autonomous Agents by Nitivra

Canonical configs, fanned out to all your AI coding agents from the Commons, the canonical ~/.agents directory

Find open-source repositories used by coding agents and thank them with human-approved GitHub Stars.

High-performance dual-engine (Rust + Python) tool call parser for DeepSeek R1/V3, Claude 3.7, Qwen 2.5, Llama 3, OpenAI & ReAct formats with auto-repair and zero dependencies.

LangGraph producer for agent-topology documents

Python utilities for the agent-topology document contract

Time-travel debugging and causal RCA for LangGraph agent traces, on a causal graph.

Generate and share self-contained HTML views of agent transcripts

Local real-time speech-to-speech translation pipeline (VAD -> streaming ASR -> translation -> TTS) for Intel AI PCs.

Authorization boundary and security regression testing for AI agent tool calls (MCP): decide on arguments against delegated authority, bind decisions to single-use grants, replay, and pin denials as CI tests. Experimental.

DSA-Optimized AI Knowledge Bank MCP Server

Human-in-the-loop for LangGraph, Pydantic AI and Strands agents -- and anything else a run has to wait for. Get the interrupt out of the process (SNS, SQS, EventBridge, DynamoDB, webhook) with everything needed to answer it; get the answer back in.

AWS announce adapters for agent-wait: SNS, SQS, EventBridge, and DynamoDB (the question as a row), plus a CDK stack for the example.

Manage isolated Python environments and Git worktrees across projects

Move a project directory and take its Claude Code, Codex and Antigravity CLI history with it.

Core framework and SDK for agent2 (headless, no TUI dependencies)

Terminal User Interface (TUI) for agent2

A local, source-cited course vault for AI agents

Inspect and improve AI agents with measured fixes and custom scores.

Agent Badge Python SDK — HTTP client for the Agent Badge API

Agent Badge CLI — enroll, patch, verify, jwks commands

Agent Badge canonical business logic: crypto, schemas, credentials, revocation, AgentCard patching

AgentScope long-term memory middleware backed by Agentbase Memory

Self-hosted code execution sandbox for AI agents

Cross-session messaging between coding agents on the same machine (Claude Code, pi, opencode, kiro, codex, antigravity, hermes, and any MCP host).

AgentScan —— AI Agent 安全检测平台：真实探测区分 AGENT 与裸模型，托管沙箱工具做注入/泄露/越权/外带（DNS+HTTP 金丝雀）/MCP 投毒多维检测，输出带真实证据的报告（支持本地与 docker 目标）

Alias package: installs agent-conformance (the Agent Conformance Engine) so that `pip install agentce` works.

Evidence emitter library for the Agent Conformance Engine (canonical CloudEvents + JSON-LD). Placeholder release.

KMS-backed configuration storage for AI agent applications

Controller-owned authorization and independently verifiable containment for AI agents

Plug-and-play turn-metrics logging for LangGraph/Strands/CrewAI agents on Bedrock AgentCore, shaped for CloudWatch Logs Insights + Grafana dashboards.

Crash-test your AI agent in a synthetic workplace. An open-source agent security test harness with synthetic tools, visual evidence, and regression tests.

Read-only native CrewAI tools for the AgentDomain MCP server

Application performance monitoring for AI agents: flows, cost, reliability and process quality

Agentevo SaaS (TZ-3 control plane, TZ-4 managed intelligence): auth, metering, C2 APIs, workers.

Agentevo core domain contracts: classification, canonical events, learned objects, trust states, errors. No I/O.

Agentevo local runtime (TZ-2): capture, DLP, encrypted vault, recall, guards, execution.

Agentevo client SDK, CLI, and agent adapters with conformance fixtures.

The trusted finite-element workflow for every MCP-compatible AI agent.

Agent-native, vendor-neutral governance, security and compliance control plane for AI agents in production.

Python SDK for AgentGate x402 — web scraping, prompt injection guard, domain intel. Auto-pays via USDC micropayments on Base L2 / Solana.

Discover AI agents, map their capabilities, and flag security risk. Read-only static analysis.

Atlassian Teamwork Graph (twg) connector for AgentGraph

Developer SDK for AgentGuard runtime governance and policy enforcement layer

Official Python Client SDK for AgentGuard MCP — Agent Reliability & Security Infrastructure

Production-quality Python SDK for integrating AI agents with AgentGuard.

MCP server exposing AgentHive's shared team memory as native tools for Cursor and Claude Code

Cross-tool agent session HUD for Cursor, OpenCode, Freebuff, Codex, and more

AI-powered bug bounty hunting — recon to report, in your terminal.

Run, watch, and meter Claude Code, Codex CLI, Gemini CLI, OpenCode, and Kiro from one CLI — verified cost tracking, token usage, budget caps, OTel gen_ai spans, Langfuse traces, and a live dashboard + MCP server.

File-based work tracking and knowledge base for AI coding agents

Function-level CRAP analysis for Python using LCOV coverage.

A standalone, framework-agnostic evaluation and scoring engine for LLM/agent outputs — extracted from AgenticLens's evaluation module.

Task-conditioned, budgeted initial workspace observation for CLI agent harnesses

An MCP server that adds terminal capabilities to an agent.

An MCP which adds terminal capabilities to an agent

an MCP which adds terminal capabilities to an agent