Python agents

Multi-model LLM Council (Karpathy-style 3-stage deliberation over OpenRouter), exposed as an MCP server for Claude Code.

Markdown corpus retrieval engine: watcher, indexer, hybrid search, MCP server.

Official Python SDK for Micro-SaaS AI Agent Suite (14 Serverless AI APIs).

Mistral AI Studio evaluation tools

Evaluation plugin for Mistral Workflows - run evaluations as parallel Temporal activities

The coding agent that grows its own tools. Watch it molt.

A Mixture-of-Models OpenAI/Anthropic-compatible LLM gateway that fans out to a panel of models and synthesizes one answer.

A knowledge engine for AI agents: your documents become a git-versioned markdown knowledge graph an agent navigates over MCP, instead of flat vector search.

Can one basin do it all? Pit Thermal Energy Storage (Xiang et al. 2022, Vojens seasonal + Hoeje Taastrup weekly), Aquifer Thermal Energy Storage (Dutch deployment scale), reservoir-supplied wetland environmental flow (Akbarichegeni & Yosefvand 2026), and navigation-weir/wetland connectivity (Hein et al. 2016's real Danube data, -68% floodplain loss) -- then honestly documents that no literature-demonstrated case integrates all of them in one structure, no UTAC/CREP bridge

Local, auditable coordination and decision tracking for human and AI-agent teams

OpenAI-compatible HTTP API for the Needle 2 tool-calling model

mini-SWE-agent adapter for NeMo Fabric

Governance for AI agents: deny-by-default tool gating, L0-L4 guardrails, human approvals and a full audit chain — via the agent-governance sidecar.

FarStars（远星）· norpagent — pluggable component-based agent framework: modular architecture layers with address functions, np() single-call startup, 9 layers / 29 hooks, norpagent.safe() decoupled security, process-level plugin isolation, ready-to-use preset modes, Central Nervous Bus (CNB) multi-instance neural tree (cortex control / freeze quarantine / subpoena evidence / behavior baselines)

Identity-aware Nowledge Mem connector for LangGraph and LangChain agents

Force local Ollama models to output strict, valid JSON. Auto-strips markdown fences and retries on failure.

See what your local Ollama model is actually doing: live prefill progress, ETA, tok/s, and how long a whole agent turn takes.

Log, budget, and visualise token usage for local Ollama models.

Ontology-first RAG: extract a governed knowledge graph from documents and serve it over SPARQL and MCP.

Vendor-neutral Governed Contracts for verifiable agent authority, constraints, conformance and consequence.

Reference validator and applicator for the Open Agent Profile (OAP) specification

Translate maps between Open Doctrines and Greater Diplomacy 5

Python interoperability utilities for OpenAgentFence security traces (early development)

Haystack integration for Opensolr — managed Apache Solr DocumentStore with server-side embeddings and hybrid BM25+kNN retrieval

Local-first LLM serving for software that has to work: a resident engine, typed errors, validated extraction and an OpenAI-compatible API — on hardware you don't control, with data that can't leave.

Python SDK for the Orion Rust agent runtime pilot

An interactive terminal Agent that can build Python applications.

Paraglacial and geophysical hazard science -- GIA/seismicity context (Grosset et al. 2023), permafrost-driven rock-slope instability (Fey et al. 2025, Gruber & Haeberli 2007), and GLOF exposure (Taylor et al. 2023, Lutzow et al. 2023) -- companion to glacial-seismicity-utac (P101), no UTAC/CREP bridge

parakeet-index llms LiteLLM integration

Open-source in-process governance for AI agent frameworks: Cedar-governed model/tool calls via build_middleware()/GovernedAgent, plus the Cedar engine, request/decision shapes, PEP<->control-plane protocol client, and Ed25519 PEP identity they run on.

Stateful agent loop with tool execution and event streaming, built on pi-ai

General-purpose agent with transport abstraction, state management, and attachment support (Python port of @earendil-works/pi-agent-core)

Coding agent CLI with read, bash, edit, write tools and session management (Python port of @earendil-works/pi-coding-agent)

Prism Network GPU tools for AG2 and AutoGen agents

Prism Network GPU tools for CrewAI agents

Prism Network GPU tools for LangChain and LangGraph agents

Public standalone LangGraph runtime for Prompt2Agent workflow exports

Phase-Shifted Agentic Swarm (PSAS) methodology for multi-agent cognitive synchronization

Package for deploy LLM Model Service

Durable execution of Pydantic AI agents on Postgres via pgtask.

pytest for AI agents — trajectory-level recording, replay and assertions for LangGraph/LangChain agents

Evaluation and quality-gating layer for RAG pipelines governed by Microsoft's Agent Governance Toolkit (agent-rag-governance)

Add your description here

Identity-aware contract testing and release assurance for enterprise RAG systems

dbt for RAG — declarative, incremental, tested embedding pipelines

A modular, provider-independent execution kernel for building composable RAG systems.

A modular Retrieval-Augmented Generation framework.

Zero-dependency RAG sanity check: score faithfulness, relevancy, and completeness in one function call. No API key, no ML libraries, no reference answers required.

Zero-config LangGraph graph visualizer

Minimal Haystack component for the Reserp Google Search API v2

Runtime enforcement library for autonomous AI agent systems: constraint enforcement, auditable decision traces, defense-in-depth safety controls, and fail-closed network resilience.

Central marketplace catalog for Sanhe's Claude Code plugins, each developed and released from its own repository.

A modular, extensible agent framework for software engineering and scientific computing tasks

PostgreSQL implementation of the Strands Agents Storage interface — durable bytes-under-keys for sessions, context offload, and memory

MongoDB implementation of the Strands Agents Storage interface — durable bytes-under-keys for sessions, context offload, and memory (aka strands-mongodb-storage)

PostgreSQL implementation of the Strands Agents Storage interface — durable bytes-under-keys for sessions, context offload, and memory (aka strands-postgres-storage)

AgentVigil/WebSentinel indirect prompt-injection optimizer for superred agent targets

Environmental Injection Attack optimizer for SuperRed web agents

Telegram context for coding agents: local sync, FTS5 search, attachments, links, threads — a tg-cli fork with an agent skill

A filesystem-native, version-controllable long-memory paradigm for AI agents. Surface/Middle/Deep layers + recall/writeback/consolidate protocol. Pure Markdown, zero infra, drives agent self-evolution.

Tianshu - Async AI Execution Platform

CrewAI adapter for tracegc context compaction

LangGraph adapters for tracegc

Storage adapters for tracegc

An MCP which adds terminal capabilities to an agent.

Constraint-aware genetic optimization for UAV area-coverage routes

Vinf Agent · 个人认知外延系统（开源版）

Full-stack agent framework for Viveka Sutra — HTTP, MCP, and queue actions

Local-only monitoring and recording UI for a Tesla Wall Connector Gen 3

Watchlight Agent SDK — build governed AI-agent plugins for any framework

Remaining LLM providers plugin (RFC-0019, M6): OpenAI-compatible presets + Bedrock + Vertex, no new architecture

Object storage plugin (RFC-0019, M9): S3, Azure Blob, GCS, OneDrive behind one ObjectStore contract

Cross-language AI enterprise agent runtime (meta-package)

Haystack integration for the You.com Search API

ZaiNar Halo MCP server — FastMCP tools and resources for RF proximity awareness

Lightweight provider-agnostic agentic coding backend (CLI + server) for the NanoCode VS Code extension.

ADAPT-Agent: Adversarial Defense & Policy Training for LLM Agents - A comprehensive library for LLM agent optimization and security

Turn-key AutoGen (AG2 / autogen-agentchat) and Microsoft Semantic Kernel middleware for the Aegis Invariant Kernel: deterministic tool-call safety clearance

Turn-key CrewAI middleware for the Aegis Invariant Kernel: deterministic, sub-2ms tool-call safety clearance for crews, agents, and tools

Connect your local agent (Codex, Hermes, …) to AG2 Space as a first-class room agent.

Static analyzer for confused-deputy vulnerabilities in MCP, LangGraph, OpenAI Agents, and CrewAI systems

Official Python client for AgentBrowser — a browser that acts on your agents' behalf.

Inter-agent messaging bus for Claude Code, Grok, OMP, Codex and others

Token, cache and context observability for AI coding agents.

Agent Data Gateway — 让 Agent 获得可信、完整、可追溯的数据输入（摄取编排层，不是 parser）

Deterministic validation of AI-agent completion claims against evidence and authority requirements.

Security and canonical authorization infrastructure for AI agents and automated tool use.

A portable agent harness and supervisor orchestration loop for raw LLM backends and multi-agent frameworks.

Turn structured agent output into polished, self-contained HTML artifacts

Catalog-backed API key loader for coding agents

Signed, verifiable AI-governance measurement card (Ed25519 receipt-spec). Measurement, not certification.

Allowlist-based task packets for Hermes, OpenClaw, and other AI agents

Offline, bounded claim-to-evidence receipts for agent handoffs

A deterministic, subscription-aware coding agent scheduler

Time-travel debugging for AI agents — OTel-in / replay-out.

Capture coding-agent transcripts to disk and expose them as SQL.

Agent-agnostic adversarial panel, ULTRA build loop, command broker, and proof gates for AI agent systems

Universal Bridge & Autonomous Agent Runtime Between Web/Cloud AI Gateways & Windows OS

EU AI Act Article 12 audit trails for AI agents