Python agents

Official Python SDK for Make Your Agent (MYA) — build AI agents with knowledge bases, tool execution, streaming chat, and per-session token usage

Managed Deep Agents — the define_deep_agent authoring interface plus the CLI that compiles and deploys a code-first Deep Agent repository to a managed LangGraph runtime.

RAG implementation pipeline with GPU support

Platform-specific compiled core extensions for myrm-agent-harness

Platform-specific compiled core extensions for myrm-agent-harness

Enterprise-ready, SaaS-native Python multi-agent framework

A thin, opinionated, local-first structured-output + logging layer over LiteLLM

Neo4j graph-store backend plugin for the Orchid AI framework

Privacy-Preserving Phragmén Voting via Secure Multi-Party Computation

CLI + library to audit and benchmark RAG pipelines

Lighthouse for RAG systems - diagnose and fix your retrieval pipeline

Generic async LLM gateway with concurrency, retries, and JSON helpers

Out-of-tree vLLM KVConnector for SemBlend semantic KV donor discovery

One unified API for OpenAI, Anthropic, Google, DeepSeek, and xAI with simple fiat billing.

Deterministic governance component for Haystack pipelines — policy enforcement, PII detection, cost tracking, and structured audit evidence. No LLM in the governance path.

Keyword-driven paper search assistant that exports slides, summaries, and BibTeX.

Toroidal semantic graph retrieval for measurable multi-hop RAG trade-offs.

MiniMax plugin for vision agents

Qdrant RAG integration for Vision Agents with hybrid search

Small, reviewable, validation-gated agent skills for Codex-style project work.

Deterministic agent test recorder and replayer. Record live runs, replay as mocks. Zero dependencies.

Python SDK and CLI for the AgentGraph trust and identity platform

An MCP which adds terminal capabilities to an agent.

Generate and safely update AGENTS.md and RUNBOOK.md for coding agents

AgentTrace Python SDK - Drop-in tracing for any AI agent

FastAPI middleware for AgentVisa AI agent verification

LedgerProof adapter for the Anthropic Python SDK. Side-channel transparency receipts for EU AI Act Article 50.

Solo Founder OS agent #4 — keep EN/ZH locale JSON in sync via Claude + HITL markdown review.

Streaming JSONL cleaner for LLM fine-tuning datasets.

Python SDK for controlling visible ChatGPT Chat and Work through a local backend.

Maintains information quality for agentic workflows — assesses the freshness, provenance, fidelity, and task-specific validity of claims, then refreshes or repairs degraded ones before agents consume them.

Solo Founder OS agent #11 — monthly bill audit across Vercel / Anthropic / Supabase / OpenPanel / HyperDX. Flags underused SaaS + spend spikes.

Solo Founder OS agent #9 — triage user messages (signup-broken / forge-stuck / billing / love / spam / novel) → auto-draft replies → HITL queue.

Generate DSPy Signatures from any prompt using a DSPy meta-program

Generate environment maps (services, artifacts, env vars) for LLM decision-making

CrewAI Tool adapter for Fetchium — token-efficient AI-native web search

LangChain Retriever adapter for Fetchium — token-efficient AI-native web search

MCP server for processing audio and video files using Google's Gemini multimodal models

A secure Gemini AI gateway client for school projects using a short import name.

Halo host adapter for LangChain agents and LangGraph graphs (Python): a wrap_tool_call encode middleware plus a halo_fetch navigation tool. install_halo() wires it in one call.

CrewAI tools for iwant.fyi -- reference implementation of the iwant.fyi demand-side protocol v1.0. Lets any CrewAI agent express structured purchase intent and receive matched supply.

LangChain tools for iwant.fyi -- reference implementation of the iwant.fyi demand-side protocol v1.0. Lets any LangChain agent express structured purchase intent and receive matched supply.

Claude Agent SDK integration for KAgent with A2A server support

Keycloak Identity MCP Server and Agent for Agentic AI!

LedgerProof callback handler for LlamaIndex — Article 50 transparency receipts for RAG and agent workflows.

Connect with Claude Code, Codex CLI, and Gemini CLI — a local prompt timeline with AI-powered prompt enhancement and revision.

Python routing library for local LLM agent loops: score prompts, map tiers to model names, embed in your runner.

Production-grade memory infrastructure for AI agents — storage-agnostic, self-evolving, observable.

MyAI Local Agent — connects your machine to the MyAI cloud AI coding assistant

LedgerProof adapter for the OpenAI Python SDK — emits Article 50 transparency receipts as a side channel.

Solo Founder OS agent #11 — overdue invoice reminders with HITL gating. Stripe-shaped types; works with or without a Stripe key (mock provider for dev/dry-run).

Curses picker for resuming Claude Code sessions

REF Agents — AI-powered SDLC governance for the Relay Engineering Framework. 19 expert personas enforcing quality gates via Model Context Protocol (MCP).

MCP wrapper for controlling Codex app-server threads, turns, plan mode, and steering.

Solo Founder OS agent #3 — draft personalized cold emails to investors (vc mode) or paying customers (customer mode), HITL queue + SMTP sender. Merged customer-outreach-agent in v0.9.0.

Lean async gRPC client for the vllm-grpc frontend

gRPC frontend server exposing vLLM's V1 engine over protobuf/gRPC

Generated protobuf/gRPC stubs for the vllm-grpc frontend, proxy, and client

REST-to-gRPC proxy server for the vllm-grpc frontend

Fail-soft engine for agent workflows written in Python — drives an agent CLI through a checkpointed state machine, unattended for days.

Self-improving AI agent with memory, skills, MCP, CLI, and TUI

Official Python client SDK for the Agent Ready API — scan any URL for AI agent-readability (Vercel Agent Readability Spec, llmstxt.org, agent-protocol manifests).

npm for your coding agent. Install packs of skills, subagents, and hooks into any repo, for every major agent.

A tiny, provider-agnostic framework for building tool-using AI agents.

Local-first observability + eval for AI agents: trace runs, detect loops, render an HTML report. No backend.

AgentTrust ID SDK — runtime authorization, opaque agent tokens, and Guardian checks for AI agents

AlgoVoi payment guardrail provider and tools for CrewAI

This is a reserved placeholder package to mitigate dependency confusion risks.

A hierarchical multi-agent harness that autonomously audits a codebase, finds high-value improvements, and applies them in TDD-gated iterations.

Give Claude total recall of its own un-compacted conversation — extract, search, and recall Claude Code transcripts.

Storage-agnostic file-editing tools (view / str_replace / insert) for Datasette Agent plugins

Universal agent server. Wraps any LangGraph graph and exposes it over standard agent protocols — Vercel AI SDK, Claude Code, TUIs, and more.

Persistent vector memory store for DSPy-powered AI agents — extract, store, and recall structured memories from conversation.

A self-hosted, long-running AI agent runtime with memory, skills, plugins, and multi-channel integrations

A agent to facilitate querying and processing finance data.

Fragmented memory system for Hermes Agent — automatically retrieve relevant memory fragments and inject them into conversation context

Lightweight client for FreeModel's Claude endpoint with retry logic, graceful error handling, and extended thinking support.

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Halo host adapter for the OpenAI Agents SDK (Python): a call_model_input_filter that swaps large tool results for a shape map (out of context) plus a halo_fetch navigation tool. install_halo() wires it in one call.

Islo (islo.dev) sandbox integration for Deep Agents

LangChain tool and document loader for Lyrenth: read URLs as clean AIDocuments.

Persistent user memory for LangChain and LangGraph agents, backed by MemoryRouter

Language analyser for trivia questions — parse, classify, and score question difficulty

CrewAI integration for LatchGate — execution security kernel for AI agents

LangChain integration for LatchGate — execution security kernel for AI agents

OpenAI Agents SDK integration for LatchGate — execution security kernel for AI agents

LlamaIndex reader for Lyrenth: read URLs as clean AIDocuments.

A local toolkit for training tiny GPT models on your own data.

MCP server giving AI agents controlled GitHub access with policy guard and audit trail

MSS-Agent: AI Agent framework with meaning-field self-check, streaming, and local encrypted vault

Neuroplastic memory, self-healing, and critical reasoning for AI agents — a local-first, framework-agnostic runtime.

PyMuPDF Utilities for LLM/RAG with Visual Analyzer

Agent wrapper for radegast EDR — syncs detection packs and forwards encrypted alerts

LangChain (Python) callback handler that adds RANKIGI cryptographic receipts to every LLM, tool, agent, and retriever step.

LiteLLM CustomLogger that adds RANKIGI cryptographic receipts to every model call routed through LiteLLM.

Remove Gemini sparkle watermark from videos