Python agents

Zero-instrumentation, fully local X-ray for coding-agent sessions: interactive timeline, tool-call tree, token/cost curves and failure highlights in a single shareable HTML file.

Agno tools for SwarmMemo, the message board and coordination layer for AI agents.

Dependency-light Python utilities for GPT, agent, retrieval, and tool pipelines.

Axon — 单用户 CLI Agent Harness：沙箱工具网关、双模型接入、可续跑与项目记忆

An append-only, signed ledger for AI agent delegations. ARD finds agents, A2A talks to them — this records who authorised the work, within what limits, and how it ended.

Risk modeling for AI agents from logs: replay a proposed change over logged episodes and separate what the log settles, what a declared stop valuation fixes, and what needs bounds.

Token-efficient remote execution, AST outlining, and safe patching tool for AI agents.

Developer-first runtime authorization SDK for AI agent tool calls. / 面向 AI Agent 工具调用的开发者优先运行时授权 SDK。

Provider-agnostic contracts for AI LLM Kernel.

Shared implementation for AI LLM Kernel providers.

Provider selection and dynamic loading for AI LLM Kernel.

Moves to another candidate after a retryable failure.

Anthropic provider for AI LLM Kernel.

Cohere provider for AI LLM Kernel.

Google GenAI provider for AI LLM Kernel.

Groq provider for AI LLM Kernel.

LM Studio provider for AI LLM Kernel.

Mistral provider for AI LLM Kernel.

Ollama provider for AI LLM Kernel.

OpenAI provider for AI LLM Kernel.

Chooses a client and model before the call.

Shared provider contract suite and fakes for AI LLM Kernel.

Runs injected tools in bounded generation loops.

Local developer telemetry agent for Antigravity AI usage and engineering signals

Python SDK for the AICE Agent Platform (config-driven LangGraph agent runtime)

Graph and execution monitoring for LangGraph workflows

Give an AI agent a verifiable AIDR identity: enroll from code, sign requests, LangChain and LlamaIndex tools.

A stdio FastMCP server for Google's Gemini API

带插件系统的 CLI 大语言模型推理接口

Run prompts and workflows approved in AirPrompter on your own systems: signed pull-only updates, an encrypted restart-safe slot store, offline operation, content-free telemetry. The facade over airprompter-agent-core, -sync, -runtime and -telemetry.

Serve a verified AirPrompter agent release: slot resolution under the ramp and any retreat, rendered text with run references, provider wrappers, and the hosted-execution client. Renders and assigns over a bundle the customer loads with no store, daemon or network.

Pull and hold AirPrompter agent releases: signed pull-only updates, the encrypted restart-safe slot store, key providers, the apply policy and its windows, and the daemon client.

The content-free telemetry spool and its uploader for AirPrompter agents: minute windows as append-only segments (or in memory on serverless), the host budget, and direct-to-object-store upload under a grant.

AEAP Composition Boundary Adapter for the Claude Agent SDK. Thin wrapper that attaches the Runtime Decision Point to agent tool invocations — especially useful for coding agents.

AEAP Composition Boundary Adapter for CrewAI. Thin wrapper that attaches the Runtime Decision Point to CrewAI tool invocations.

AEAP Composition Boundary Adapter for LangChain. Thin wrapper that attaches the Runtime Decision Point to LangChain tool invocations.

AEAP Composition Boundary Adapter for LangGraph. Thin wrapper that attaches the Runtime Decision Point to LangGraph node invocations.

AEAP Composition Boundary Adapter for the Microsoft Agent Framework. Thin wrapper that attaches the Runtime Decision Point to agent middleware and workflow execution.

AEAP Composition Boundary Adapter for the OpenAI Agents SDK. Thin wrapper that attaches the Runtime Decision Point to agent tool invocations.

Akeyless Agentic Runtime Authority (RTA/ARA) for AWS Bedrock AgentCore — secretless DB and cloud actions

Find edits a coding agent made against a stale view of a file, and keep agents' views current with a write-through hook (Claude Code, any hook system, any MCP client, mini-swe-agent)

Official Python SDK and CLI for Allevitas AI agent platform

All your mailboxes in any AI agent, over MCP. Runs locally; nothing is sent or trashed without your click.

Native Linux desktop client for Docker Engine

Grounded answers, or an honest escalation. A dependency-free hallucination gate for RAG chatbots.

Self-contained, obliterated AI agent on your own GPU: memory, document RAG, tools, MCP, maps, multi-user via vLLM.

Aphasia Agentry - canary-proven breach and attack simulation for AI agents (OWASP LLM Top 10)

Catch hallucinated and deprecated API usage: AST scan plus real importlib existence checks

Name reserved by Blugrid Pty Ltd for a private package. This placeholder does nothing.

Autonomous AI Agent SDK for ArcNano Shielded Zero-Knowledge Nanopayments on Arc

Installable Ariadne Agent backend: fixed-role conversations over native Ariadne tools

Autonomous text-to-music composer driven by a multi-agent ReAct harness (Claude API, with an offline deterministic fallback).

An extensive Model Context Protocol (MCP) server for driving Aseprite (pixel-art editor) headlessly via Lua scripting and the Aseprite CLI.

A verifiable LLM agent for hierarchical molecular-cloud catalog analysis

Deterministic astronomical FITS processing with reproducible pipelines and provider-independent planning

Composable RAG pipelines for AI agents: splitters, embedders, vector and keyword indexes, hybrid retrieval, reranking and retrieval patterns, built from a YAML spec.

Haystack components and agent tools for Asyntai, the AI chat agent for websites

Standalone client library for Atellagent

Microsoft Agent Framework tool guard for Atlas Proof-Carrying Authority (PCA): make every tool/function call proof-carrying and policy-gated

CrewAI tool guard for Atlas Proof-Carrying Authority (PCA): make every CrewAI tool call proof-carrying and policy-gated

Haystack (deepset) tool guard for Atlas Proof-Carrying Authority (PCA): make every Haystack tool/ToolInvoker call proof-carrying and policy-gated

LangGraph tool/node guard for Atlas Proof-Carrying Authority (PCA): make every graph tool/node call proof-carrying and policy-gated, with interrupt()-based step-up for risky nodes

Proof-Carrying Authority tool guard for Pydantic AI (verify a PCActn before each tool runs)

Toolkit modular de auditoría técnica en Python (solo stdlib)

LiteLLM usage adapter for AUDR (experimental)

Auth Your Agent SDK: let AI agents act for a user on websites, with the user's approval on their phone.

Full 5-pillar NTI post-quantum security for AutoGen and Microsoft Agent Framework.

Microsoft AutoGen tool integration for WarpPay402 x402 monetized APIs

Python client and CLI for AutoML-Agent: describe an ML task in one sentence, get a verified, deployable pipeline.

Async, event-driven library of production-deployable agent algorithms over arbitrary data.

AAA, Autonomous Agent Architecture: the architecture and runtime for autonomous agents. Build, orchestrate, execute, recover, manage.

A developer-first PyTorch engine for explicit, modular LLM training. Zero magic.

Backstage Agents SDK — conversas, custo e eventos de agentes Python para o Backstage

A reliable Python agent loop with tools, retries, transcripts, and observability.

Tools for agentloop agents: native web search now; client search and coding tools next.

Agent configuration, instances and local composition

Agent configuration and local conversation-review commands

Shared explicit storage contracts and backend selection

Provider-neutral building blocks for reliable AI agents

AWS-native resilience layer for Amazon Bedrock: cross-region and cross-model failover with schema validation.

Privacy-first policy enforcement for generative AI traffic

BedrockPlus server command and typed Python plugin API

Python client for BehaviorGPT, UnboxAI's Large Behavioral Model for search, recommendations and personalization

Ask which benchmarks researchers use, how usage changes, and which new benchmarks are adopted

Bilibili command-line tool designed for AI agents: JSON output, stable error codes, zero interaction.

Name reserved by Blugrid Pty Ltd for a private package. This placeholder does nothing.

The Booking Agent CLI: a stateful USP booking flow with hard gates, plus its USP protocol library.

An agent SDK for config-driven chat agents

No-code synthetic LLM training dataset generator

RAG retrieval and citation steps for BrainForge inference pipelines

Programmatic LEGO design

Early draft reference implementation of BYOA (Bring Your Own Agent): manifest validation and the call gate.

Python SDK for the brisvox agent protocol: the application logic of a real-time voice call (tools, events, commands) in async Python.

Real headful Chrome on Xvfb with a hardware-level X11 mouse, Cloudflare Turnstile auto-solve and zero-leak CDP. Localhost HTTP API + CLI + Python SDK.

Per-user, per-feature and daily spend limits, plus loop detection, for OpenAI and Anthropic SDK calls.

Small building blocks for Python agents and harnesses

Name reservation for the Byteplus Python SDK split package byteplussdk-llmshield

CairnML agent - runs queued CairnML jobs (an unofficial fork of ClearML Agent)

Once-only actions, approvals bound to exact arguments, and record/replay for Python AI agents