PyPI agents

Production-to-dev bridge. Ingests logs/errors from observability tools, clusters them, asks an LLM to summarize each cluster, opens or updates issues on GitHub/GitLab. Optional handoff to relay-agent closes the full SDLC loop. Standalone: no inter-package runtime deps.

Disk-backed Storage adapter for Causeway — dev + tests.

Compatibility shim for the renamed chenyuguo-agora-agents-exp package.

Real-time cross-machine MCP relay for Claude Code agents — send and receive messages across named channels.

MCP server exposing claude-full-stack-2.0's 84 architecture and implementation skills + 4 workflows as MCP tools — making them invocable from Claude Desktop and any MCP host.

CLI para gerar Custom Agents (VS Code + GitHub Copilot Chat) em qualquer projeto.

Monty-backed Python REPL middleware for Deep Agents, with a shared filesystem between the sandbox and the agent's file tools.

Flake8 plugin for detecting static-analysis escape hatches in Python code

Groq Whisper 多 Key 并发语音转写 CLI 工具

Reserved package

Maintain a local, LLM-queryable corpus of an IETF Working Group's public record (drafts, mailing list, GitHub issues, meetings), with an MCP server, semantic search, and NotebookLM export.

Reversible UUID/ID aliasing for LangChain & LangGraph — cut tokens and stop the LLM mangling your IDs.

LangChain integration for TinyFish Web Agent - AI-powered web automation

Capture decision-id-joined evidence from LangGraph agents. Wraps your checkpoint saver to emit OEP tool_permission_packet.v0 records covering the 19 surfaces LangGraph's StateSnapshot does not bind natively.

Causal intent monitoring for LangGraph agents using bundled Structural Final Models.

Local models management utility

LeAgent — Intelligent Office Agent Platform

Lightweight TUI manager for llama.cpp models on Raspberry Pi

Local AI coding agent — Ollama + any model

Mirror Helicone traces into LLMGovernor's anomaly engine

Mirror Langfuse traces into LLMGovernor's anomaly engine

[DEPRECATED — use llmgovernor[litellm]] LiteLLM callback for LLMGovernor

OpenTelemetry span exporter for LLMGovernor

Catch AI code hallucinations before they ship. The linter for AI-generated imports.

Compressed vector index for RAG pipelines — 7-10x storage reduction, no training required

Python SDK for Codex

AI agent framework for data analysis — write and execute Python code to answer questions about data

Local RAG indexer and MCP server for AI coding agents (Claude, GPT, Gemini, Cursor, Factory Droid, and more).

Ollama-based embedding + retrieval pipeline backed by skeg.

A fast multi-source, multi-target skill manager.

Lightweight API key proxy for llama.cpp server with token usage tracking

Stet Harbor support agents

MCP server exposing Stripe APIs as structured tools for Claude and other agents

Thin AI agent harness — self-evolving, Claude Code-style memory

AI code/PR review agent. Fetches a pull request, asks an LLM to review it, posts inline comments + summary verdict back to the VCS. Self-hosted, multi-VCS (GitHub, GitLab, Bitbucket, Azure DevOps), multi-LLM (Anthropic / OpenAI / Google / Claude Code / Ollama). Standalone: no inter-package runtime deps.

Source-available CLI for semantic Taiwan legal judgment retrieval — search judgments, package them for your own AI tools, and run a bundle-level citation check. Retrieval-only; does not generate or endorse legal advice.

Uptimes Agents — OpenTelemetry-based observability for AI agents. Three-line init, ships to local uptimes-monitor or direct to api.uptimes.ai.

WuYa (无涯) — A theory-driven multi-agent system for academic paper evaluation and journal recommendation

Python SDK for AI Agent Assembly - A governance-native runtime for AI agents

Agent Commerce Protocol MCP — bridges Stripe ACP + Google AP2 + Coinbase x402 for agent payments inside ChatGPT, AP2 coalition rails, and pay-per-call x402 flows. By MEOK AI Labs.

Agent Content Watermark MCP — dedicated EU AI Act Article 50(2) GenAI watermarking. Visible + invisible + perceptual layers per the Code of Practice (2 Nov 2026 cliff). C2PA manifest envelope. By MEOK AI Labs.

Agent Cost Allocator MCP — multi-tenant LLM cost attribution for chargeback billing. Companion to agent-token-budget. Splits one agent's spend across many tenants for invoicing. By MEOK AI Labs.

Run the AI Agent QA Eval Pack against your tool-using LLM agent + grade it with a shareable scorecard badge. Deterministic, OWASP Agentic Top 10 aligned, no LLM-judge.

Agent Incident Relay MCP — Article 73 5-clock broadcaster. One incident → simultaneous signed reports to EU AI Act Art 73, DORA Art 19, NIS2 Art 23, GDPR Art 33, ISO 42001 cl 10.1. By MEOK AI Labs.

Python bindings for agentdir — virtual file tree infrastructure for agent-ready file layouts

Arize Phoenix dashboard hook for AgentForge

StatsD metrics emitter hook for AgentForge

Agentic Delivery CLI — wrapper over the scripts/* pipeline

Python SDK for AgenticSettle — verify any AI agent's output, settle with pre-paid token escrow, earn the Verified badge.

FinOps for LLM agents: budgets, waste tracking, and caching analysis for OpenAI, Anthropic, and AWS Bedrock

Deterministic record-and-replay debugger for AI agent runs

Populate an in-warehouse agents.* schema from dbt manifests, OSI YAML, LookML, and markdown skills.

AgentSeek API core runtime with OceanBase checkpoints.

Agent stock ranking and portfolio benchmark engine

Apache 2.0 reference implementation of an agent that emits an AlgoVoi settlement-attestation-v1 receipt for a Base chain transaction. End-to-end worked example demonstrating the AlgoVoi-authored substrate discipline.

Plug-and-play llama.cpp runtime for Intel Arc GPUs. Auto-detects your card, picks safe SYCL defaults, and exposes an OpenAI-compatible API.

Read-only linter for .claude/ and CLAUDE.md — measures token budget and audits agent/skill quality.

Haystack integration for Cognee — memory for AI agents

Python SDK for the agent-identity credential routing sidecar — by Datacules LLC

Multi-agent RAG system for RBAC-secured financial document Q&A. 72.7% on FinanceBench. Ships a CLI client + self-hostable FastAPI backend.

Multi-agent toolkit for analyzing and managing Google Analytics 4 properties. Works with Claude Code, Codex, and Gemini CLI.

Haystack Document Store and Retriever backed by Pixeltable multimodal data infrastructure.

A terminal-focused AI agent with RAG and local tool capabilities

Interloper AI agent powered by Google ADK

langchain-akasicdb package is an implementation of core LangChain abstraction for AkasicDB

High-level reasoning agents with planning, confidence judgement, and reflection on top of LangGraph

A framework that replace traditional RAG pipelines. Ingest any number of documents in multiple workspaces (channels, departments, etc.), index it with BM25, and let the agent search, fetch, and reason over it, exactly like searching the web, but entirely on your machine. No vector store, no embedding needed.

An MCP which adds terminal capabilities to an agent

Middleware LLM Observability — OpenInference/Opentelemetry tracing for the Middleware SaaS

Offline Expert Agent — local RAG, agent mode, plugins, privacy-first

AI-powered phone automation framework

Storage extension for PySTAC

Run parametrized test variants in parallel threads — with correct fixture lifecycle

Drop-in RAG SDK for website chatbots

Universal RAG orchestration layer with pluggable vector DB adapters

Document influence analysis for RAG systems using social network centrality measures

Standalone terminal agent daemon for RelayForge.

Multi-agent code review system using LangGraph

Purpose-scoped ADK agents for SDC4 data operations — SMB Edition (local LLM via Ollama)

Reserved package name; project under development.

A discreet, zero-dependency message bus that lets terminal AI agents (Claude Code, Codex, Grok, Aider...) talk to each other over tmux — via readable markdown threads + a doorbell.

Deterministic tool orchestration for LLM/SLM flows with policy-gated parsing.

Agent Brain UDS - Unix-domain-socket transport for Agent Brain (socket path resolution, permission validation, httpx UDS client factory)

CLI benchmark suite for evaluating AI agents across providers.

A general-purpose coordination protocol and CLI for multiple AI coding agents working on one repository.

Framework adapters for the Agent Governance Toolkit (LangChain, CrewAI, OpenAI Agents, and more)

Protocol implementations (MCP governance, trust protocol, A2A, MCP receipts) for the Agent Governance Toolkit

Retrieval access control and vector store policy enforcement for RAG pipelines

Deprecated: renamed to keys-on-the-wire. Installing this installs keys-on-the-wire.

Deprecated — use agentassert-abc[claude-code] instead.

Deprecated — use agentassert-abc[gateway] instead.

Deprecated — use agentassert-abc[proxy] instead.

Deprecated — use agentassert-abc[sdk] instead.

Enterprise-Grade CI/CD Quality Gate for LLM Agents

Discover every AI agent in your infrastructure. 5-layer detection: static analysis, network monitoring, eBPF/Kubernetes runtime, endpoint, and cloud audit (CloudTrail). Company-level correlation. AIBOM export. MCP server detection.

Agent First Interface — scaffold CLI, MCP, and HTTP interfaces for agent-first tools.

Agentic Environment & Resource Orchestrator

Release readiness gates and evidence for Microsoft Foundry agents

Make full use of every coding-agent subscription you pay for: a local CLI + MCP server that surfaces live usage limits and offloads work to providers with headroom.