Python agents

RunAPI GPT Image 2 SDK for text-to-image and image editing workflows in JavaScript, Python, Ruby, Go, Java, and PHP

SecureVector SDK for LangChain — brings the local threat monitor's three controls (tool-call permissions, secret/data-leak detection, threat detection) to every LangChain tool call, with tamper-evident audit logging.

Haystack integration for Skim — clean web reader for AI agents. Card plan with API key (free tier) or x402 wallet pay-per-call ($0.002 USDC on Base).

A small-but-complete agent harness: ReAct loop, tool injection, three-tier memory, restricted-expression panels. Zero heavy deps.

Live terminal TUI tracking Claude Code token usage and cost estimates

A self-extensible agent CLI with terminal UI, multi-provider LLM support, session management with branching, and a plugin system for tools and commands

Local editable workflow canvas for AI coding agents.

Haystack integration for whisper

Prompt-aware LLM routing-decision service: predicts which model can complete a prompt and picks the cheapest one.

Orchestrate multi-agent workflows with autonomous reasoning, parallelism, rate limiting, and LLM integration

AgentMetrics observability integration for Claude Managed Agents

AgentMetrics observability integration for AutoGen agents

AgentMetrics observability integration for CrewAI agents

AgentMetrics observability plugin for Hermes agents

AgentMetrics observability integration for LangChain agents

AgentMetrics observability integration for LlamaIndex agents

AgentMetrics observability integration for OpenAI Agents SDK

Shared event schema, pricing, and redaction for all agentmetrics integrations

Generated Ax runtime library

OpenAI Agents SDK adapter for Bolyra -- guardrails, tool wrappers, and MCP auth

The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere

Self-referential structure-learning system — agents that learn by inhabiting worlds

Dee Agent Music — CrewAI tool wrapping Dee SDK for mood-based music generation

Dee Mood Music for LangChain Agents — emotion-regulating music tools for AI agents

O(1) hyperbolic memory for any LLM — 260 bytes per session forever

Memory-backed autonomous agent with a Docker membrane, a Slack/Discord cockpit, and capability graduation.

Local-first LLM router: keep sensitive data and bulk text labor on your own models, call the cloud only for the hard part. Privacy-routing (fail-closed) + manager-worker delegation + allowlist guard, MCP-native.

Govern an AutoGen agent's native tool calls with Lodestar — the thin native hook that remotes each tool call through the Lodestar Action Kernel over NDJSON-RPC (ADR-0027).

Govern a CrewAI crew's native tool calls with Lodestar — the thin native hook that remotes each tool call through the Lodestar Action Kernel over NDJSON-RPC (ADR-0026).

Govern a LangGraph agent's native tool calls with Lodestar — the thin native hook that remotes each tool call through the Lodestar Action Kernel over NDJSON-RPC (ADR-0024).

A nano code agent built from scratch in pure Python.

Python client for Nexez agent discovery, checkout validation, and negotiation handoff.

Local and HTTP server embedding tools for multilingual E5

Combined tree/event based JSON parser

This name is reserved. Install the real package: pip install quorum-ai

The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere

SCDL-RAG: Detect and fix RAG hallucinations with 97% recall and 100% precision.

Typed, auto-generated client for the OpenSwarm product-analytics ingest API.

Typed, auto-generated admin client for the OpenSwarm product-analytics private (read/ops) API.

agent-gyrk — CLI agentic rodando o modelo GYRK (visão + plano)

Agent-friendly Markdown-to-PDF CLI with HTML preview and JSON diagnostics

Python SDK for the Optimus API — MSC construction, routing, and answers

Semantic-causal CRDT for agent-mutable world state

An MCP which adds terminal capabilities of an agent

Define agents (tools + system prompt) in YAML and run them as an orchestrated pipeline.

Least-privilege permissions for AI agents and MCP tools. Record what your agent does, auto-generate a safe policy, and block dangerous tool calls before they happen.

Local-first security scanner for AI Agent, MCP, and AI coding tool projects.

AgentShield SDK — instrument AI agents and capture execution events for the AgentShield Runtime Control Plane

Que Claude genere interfaces de usuario con A2UI en sus respuestas.

CrewAI tools for Bolyra mutual ZKP authentication and SD-JWT delegation

Namespace alias for `crewai-ceki` — install that for the real package.

Namespace alias for `langchain-ceki` — install the real package.

Reusable lessons/memory engine for Claude Code: frontmatter lessons, auto-CATALOG, offline retrieval, path-triggered lessons, auto-maintenance, parallel-session and sub-agent guards.

CrewAI toolkit for Ceki — real Chrome sessions for AI agents with persistent profiles across runs

AI-powered runtime debugging agent for Python web applications

OKF-aware virtual filesystem backend for LangChain Deep Agents (Open Knowledge Format).

Autonomous security scanner for AI agents. Detects prompt injection, tool abuse, data exfiltration, and OWASP ASI Top 10 vulnerabilities.

Compression with a quality contract — cache-aware, causally-pruned context compression for agentic runtimes, gated by a statistical non-inferiority test.

Free local AI agent: zero-setup local LLM (llamafile/GGUF), Groq, Gemini, Ollama — HTTP API, sessions, streaming, tool use

LangChain tools for the GhostCrawl web data API.

A lightweight multi-agent framework built on top of pydantic-ai.

Keenable web-search and page-fetch components for Haystack. Keyless by default.

LangChain tool for Ceki — real Chrome sessions for AI agents

Husk sandbox integration for Deep Agents

Talordata SERP tools for LlamaIndex agents.

A small package to fuzz test LLMs

Быстрый доступ к LLM через api.llm7.io без API-ключа

Renamed to cdv — a research preview of a dual-loop evaluation architecture for agentic LLM systems.

Security & quality audit for AI-agent extensions (Claude Code skills, MCP servers, plugins) — scan before you install.

基于 Ollama + RAG 的智能问答系统

An MCP server that offloads cheap work from your cloud LLM agent to a local Ollama model.

The billing layer for AI agents — self-hosted, Stripe-integrated usage metering and prepaid-credit billing for LLM/agent spend.

LLM-assisted qualitative survey coding with auditable Excel workbooks

Lightweight evaluation metrics for RAG (Hit@k, Recall@k, Precision@k, MRR, nDCG, and more)

RAGfly CLI — operate RAGfly from the terminal and CI (login + cloud API). Lightweight, no desktop dependencies.

One vLLM plugin for transparent RAIF token savings — install it and existing OpenAI clients get RAIF on tools & response_format with no proxy and no client changes.

SecureVector SDK for CrewAI — brings the local threat monitor's three controls (tool-call permissions, secret/data-leak detection, threat detection) to every CrewAI tool call, with tamper-evident audit logging.

SecureVector SDK for LangGraph — brings the local threat monitor's three controls (tool-call permissions, secret/data-leak detection, threat detection) to every LangGraph tool call, with tamper-evident audit logging.

SemantixRAG v2.0 — AI-Native Data Platform with GraphRAG, Compliance, and Observability

Spine 家族的通用多 agent 协作框架:agent / tool / 编排 + MCP / A2A 协议缝(离线优先,依赖 corespine)。

Pluggable multi-layer LLM jailbreak defense pipeline

MCP server bridging the Antigravity (agy), OpenAI Codex, GitHub Copilot, Cursor, Grok Build, and Kimi Code CLIs so Claude Code can drive them as sub-agents

Python client for Agent Payment Guard

Server SDK for agent-phonon — orchestrate AI agents across multiple devices.

Centralized API provider management for AI coding agents

A zero-dependency skill memory, testing, and refinement engine for AI agents.

AgentAuth — attested identity and verifiable execution receipts for autonomous AI agents

AgentGuard — AI Code Security Scanner + Auto-Fixer

Deterministic log templating on top of Drain3, packaged as an artifact for AI agents.

#An MCP which add terminal capabilities to an agent

A friendly, batteries-included toolkit for building AI agents in Python.

Shared sensing contract for AI-agent graders — the verdict/report/intent/handoff models and the Sense protocol behind AgentVision (eyes), Audel (ears) and Verel (brain).

Turn any project idea into a verified, sprint-ready agile task board — inside your AI coding agent

Open, content-addressed agent identity references bound into the pinned AlgoVoi substrate (agent_id + issuer + scope + validity window; L1 frozen)

A practical Python toolkit for building production-grade AI agents with Plan-Execute, Error Reflection, Tool Routing, Dashboard, Access Control, MCP Server, StateGraph, CrewRole, and TypedAgent.

Serverless radar for Amazon Bedrock — deploy a Lambda that logs prompt/latency to S3, then analyze it.

Haystack integration for Azure Document Intelligence using the Form Recognizer SDK

MCP server exposing the Modern-Expo virtual Business Analyst Knowledge Base (read/derive tools).

Track warm/cold status of Claude Code sessions in a dedicated DuckDB file