Python agents

CHAP adapter for Pydantic AI: record a human-decision envelope when a run pauses for tool approval.

A lightweight CLI coding assistant agent

Reserved name. Cirrus Networks internal package — not distributed on PyPI.

Haystack document store backed by Citadel: encrypted at rest, with deletes that destroy the key

LangChain vector store and chat history backed by Citadel: encrypted at rest, with deletes that destroy the key

LlamaIndex vector storage backed by Citadel: encrypted at rest, with deletes that destroy the key

Microsoft Agent Framework chat history backed by Citadel: encrypted at rest, with deletes that destroy the key

OpenAI Agents SDK sessions backed by Citadel: encrypted at rest, with deletes that destroy the key

Strands Agents session storage backed by Citadel: encrypted at rest, with deletes that destroy the key

Subway Surfers while Claude Code is thinking: a generated 3D gameplay strip beside your terminal

Convert Claude Code transcript JSONL files to HTML, with a trajectory timeline view and opencode support (fork of claude-code-log)

Scrub Claude Code session JSONL files for safe publication.

Back up and restore your Claude Code configuration (skills, plugins, hooks, settings)

Browse your Claude Code sessions and project memories: a terminal table and a self-contained HTML page.

A live reading pane for Claude Code sessions: only the text Claude writes to you, in any terminal

Read-only, spec-driven natural-language agent over any API (OpenAPI/Swagger, GraphQL, or auto-converted Postman/RAML/API Blueprint), with citations and a faithfulness check.

Estimate AI coding agent (Claude Code / Codex CLI) token usage and cost from local logs

Your AI agent says the work is done. Coherence makes it prove it — evidence, not claims, with tamper-evident CI sessions.

Cortadel memory for CrewAI — self-hosted long-term temporal graph memory as a drop-in crewai.Memory, plus native tools.

Cortadel long-term graph memory as a native Pydantic AI capability — memory tools plus automatic recall and persistence.

Multi-domain MCP Server for Voice Agent (Finance, Retail, Telecom)

Governed CrewAI tools. Your crew's tool surface is your AgentValet grant matrix, so an agent cannot form a call it was never granted.

MongoDB persistence backend for CrewAI Flows with built-in message pruning via agentstate-reducer

SQL persistence backend for CrewAI Flows via SQLAlchemy (SQLite, PostgreSQL, MySQL) with built-in message pruning via agentstate-reducer

CrewAI tools for StayingAPI: search stays, check availability, price a stay, compare prices across booking sites and read reviews, from CrewAI agents.

CrewAI integration for TokPortal — managed TikTok, Instagram and YouTube accounts as CrewAI tools (native tools + remote MCP server).

CrewAI tools for Zillapi: look up Zillow property data, valuations, schools and listings from CrewAI agents.

Stream-level supervision for AI agents: watch live token streams, interrupt mid-generation, gate tool actions pre-execution. Name reservation - the open-source release lands here in September 2026.

Automatically generate llms.txt documentation for a Datasette instance

DecimalAI's LangChain integration ships inside `decimalai` — run: pip install decimalai

Multi-agent collaboration plugin: broadcast, sequential, debate, supervisor, consensus and relay strategies over DeepSeek/OpenAI-compatible LLMs

Experimental fail-closed pre-dispatch boundary for AI agent tools.

A robust imputation plugin for Python Polars DataFrames backed by Rust.

LLM API pricing registry and cost estimation, shared by the DeepSeek Harness dsh-llm-cost plugin and Python agent systems.

Run LangGraph graphs as errand jobs — background execution, HITL resume, SSE streaming, smart retries, and an auto-generated FastAPI router.

vLLM architecture plugin for Exionos X1

Python client and framework adapters for FloAgent external apps

Python SDK for live GRAM/USDT prices and buying Telegram Stars and Premium through Fragment

Retrieval-augmented search over an Obsidian vault managed as a git repository

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

Budget checks for OpenAI API costs, locally and in GitHub Actions.

Unofficial Grafana Agent Observability plugin for Hermes Agent. Records LLM calls and tool executions as generations and OTel traces+metrics.

Grantor sovereign-tier agent SDK (agent-zk deed minting) — UniFFI-bound Rust core.

Declarative, extensible compiler from versioned YAML workflows to native LangGraph

AI agent for heliophysics and space plasma data analysis

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

IoT and low-resource packaging of Hermes Agent, maintained as a native-compatible fork

Hikari - Autonomous AI Desktop Agent for the Windows Operating System.

Install ImFusion SDK rules and skills for AI coding agents.

Python SDK for ordered Infragrid browser workflows

AI-powered Jira CLI assistant

Broker-backed, kubeconfig-free overlay for the Agentic Sandbox client.

A client library to interact with the Agentic Sandbox on Kubernetes (seamed republish).

LangGraph recording and replay adapter for Kitaru.

LLM infrastructure layer with multi-provider fallback, health monitoring, speed probing, and alerting.

LangChain middleware and two-stage dynamic MCP execution for Agent Traffic Lab

LangChain tools and retriever for AlphAI: AI-scored financial news and SEC Form 4 insider events.

An integration package connecting Blopus and LangChain

Official LangChain & CrewAI integration for CiteMesh x402 citation settlement and anti-hallucination claim anchoring.

LangChain tools for Context.dev web data, brand intelligence, monitors, and batches

DecimalAI's LangChain integration ships inside `decimalai` — run: pip install decimalai

LangChain middleware for the EISFI Weaver integrity chain: a tool call whose integrity precondition fails is never executed.

Placeholder for the LangChain integration with OpenSearch (langchain-opensearch-py). Real integration is under active development.

Minimal LangChain tool for the Reserp Google Search API v2

OpenSandbox sandbox backend for LangChain Deep Agents — run agent-generated code and file operations in an isolated OpenSandbox environment.

Tacnode integration for LangChain and LangGraph — multi-modal retrieval and a drop-in agent stack on one hybrid SQL plane

LangChain / LangGraph integration for TokPortal — managed TikTok, Instagram and YouTube accounts as tools (native tools + remote MCP server).

LangChain document loaders and byte store for XNS — S3-compatible object storage with $0 egress

A terminal CLI for browsing LangGraph checkpoints — list threads, walk state history, inspect and diff checkpoints, no code required.

MCP server that parses LangGraph Python codebases into a structural graph model and layers local semantic search on top.

A DynamoDB-backed BaseStore for LangGraph — cross-thread memory for agents, no Postgres/pgvector required

Behavioral scenario testing for production LangGraph applications

A credential-aware router that evolves which specialist to dispatch each task to, sitting above OpenClaw, Hermes, ZeroClaw, or any REST-accessible agent backend.

Itsuki long-term memory block for LlamaIndex.

LlamaIndex integration for Opensolr — managed Apache Solr vector store with server-side embeddings and hybrid BM25+kNN search

LlamaIndex tool spec for AlphAI: AI-scored financial news and SEC Form 4 insider events.

llama-index tools blopus integration

llama-index tools Live Tennis API integration — FREE-tier live scores, players, rankings and fixtures

llama-index vector_stores PolarDB-X integration

High-speed deterministic scanning for LLM inputs and outputs

Fix broken markdown that LLMs generate — tables, lists, headings, emphasis, code fences, quotes. Zero dependencies, one function.

Trace LLM calls with a decorator — non-blocking, fail-silent observability SDK.

GenAI model provenance and jurisdiction assurance harness

Black-box security scanner for LLM chatbots — OWASP LLM Top 10 red-teaming CLI

llm_velocity is a lightweight framework designed to build high-performance, cost-effective AI agents. It drastically reduces LLM call expenses and accelerates response times by intelligently optimizing how the language model is utilized.

Local-first API usage and cost tracking platform

Framework and CLI utility to create and curate datasets (e.g., publications, metadata, LLM prompts, etc.) and orchestrate (design, run, evaluate) various LLM experiments on them

Measured latency, uptime and outages of AI inference APIs (OpenAI, Anthropic, Gemini and 40+) from 4 regions — client for the open llmlatency.dev dataset

A minimal terminal client for OpenAI-compatible LLM servers.

Context-Memory Harness for AI Agents. Context Window = RAM, Local Wiki = Disk.

Local-first RAG studio powered by LumenVec

Native-first Codex subagent coordination with an optional cross-session bridge

Cost-Aware Hierarchical Coding Agent & Context Firewall — Universal MCP Server, CLI, and Python SDK

An integration of MariaDB 11.7+ (native VECTOR support) with Haystack

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

Orchestration engine for driving a fleet of headless coding agents (Cursor, OpenCode, Codex, Antigravity, Claude Code) from one driver via MCP + Skills

Runtime security proxy for MCP agent tool calls

MCP server for image generation, editing and multi-turn refinement with OpenAI gpt-image-2.5

Host-level deployment and supervision agent for the MCP Worker platform: manage local Worker services (git/pip/systemd/launchd), health polling, heartbeat aggregation, and self-healing.