Python agents

Bound what a compromised LLM agent can reach and do

Typed LLM tool definitions and dispatch for Bowline APIs

Configurable LLM annotation with adaptive batching and BOHB-style tuning.

A drop-in semantic cache for LLM APIs: match requests by meaning, serve repeats instantly, and route across OpenAI, Gemini, Groq, Claude, Ollama and Bedrock.

The production toolkit for LLM calls: caching, retries, fallback, cost tracking, security and structured output in one decorator.

One headless turn of a coding agent (Claude Code or Codex) through the vendor SDKs: explicit knobs, a deadline that kills the tree, one result.

Python SDK for the camelAI hosted agent runtime

Flask extension serving a store's pages as Markdown at /page.md and listing them in llms.txt and llms-full.txt.

Stamp out a new Claude Code agent from the canopy operating model — a self-contained, zero-runtime-dependency factory. Pip-installable into canopy / canopy-web / any second consumer.

Typed, async Python SDK for AWS Devops Agent.

Typed, async Python SDK for AWS Kinesis Video Webrtc Storage.

A small example package

Reserved name. No functionality is provided by this distribution.

Reserved name. No functionality is provided by this distribution.

Reserved name. No functionality is provided by this distribution.

Variable-level traceability checker for CDISC SDTM/ADaM submissions

Lightweight, async multi-agent framework with native handoffs for Gemini, Gemma, Grok, OpenAI & Claude.

AI Chatbot CLI with advanced sandboxed text and file system interaction

Placeholder reserving the name of an internal Cheffelo package.

An LLM agent that runs end-to-end DFT band-structure studies with Quantum ESPRESSO

Отказоустойчивый Python фреймворк для взаимодействия с LLM, валидации Pydantic и надежного парсинга структурированных ответов.

HTML to RAG-ready Markdown: a learned boilerplate filter that removes site chrome (navigation, footers, cookie banners, related links, comments) and keeps article, documentation and pricing content. Pure NumPy inference, no model download.

ChronoLLM CLI — Chat with temporally consistent language models

LLM Toolkit

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

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

Switch Claude subscriptions and API-provider keys from Claude Code

Price your Claude Code session logs and view the spend in a local dashboard

Design, preview and install a themed statusline for Claude Code

One local page showing every Claude Code session on your machine, and where they overwrite each other's memory

Local kiosk display for Claude usage and system resource stats.

A personal control plane for a Claude Code setup that spans multiple accounts and machines — memory sync, skill registry, usage reporting, and a terminal dashboard.

Pace your Claude plan limits across the week: daily budget, 5-hour and weekly meters, sessions per week.

Sandboxed Claude Code, Codex and Pi: a bubblewrap jail with an egress allowlist, via uvx

Compile coding tasks and patches into minimal evidence-complete context for AI agents.

Local dashboard for Claude Code usage: hours, tokens, project split, and a weekly-limit gauge calibrated from your own /usage readings

Are you using Claude Code well? Finds the habits and settings that waste tokens, from the transcripts on your machine.

A comprehensive, advanced pure-Python mathematics library featuring 1,400+ mathematical algorithms across 20 mathematical domains.

Hasta la vista, Claude sessions!

Connect AI agents to a live Python session (Positron, Jupyter, VS Code, or a bare REPL) over the ClaudeR protocol

Live Claude Code rate-limit view for the ClaudeWatch GNOME Shell extension

Browse, resume, and export Codex and Claude Code sessions with a Textual picker

国内大模型选择器/路由器：自然语言任务分类 × 评分矩阵推荐 × OpenAI 兼容网关路由

A Python library for building collaborative AI agents.

Codebuff JupyterLab Extension - Thin client for Agent Server

Project-agnostic agentic code coverage: measure, score, explain gaps, draft tests.

Give AI agents inspectable observations of files, images, screens, and context with receipt-backed perception.

Official Python telemetry & remote-config client for CommB (Commercial Bots)

Business acceptance evaluation for e-commerce agents

Local web control panel + live PM/Architect/Backend agent pilot for company-os-cli instances

A Spec-Driven Behavioral Contract & Verification Engine for Tool-Using AI Agents

Automatic learned skill delivery for native LangGraph agents

Run coding agents in parallel, each on its own git branch, with a supervisor that delegates, reviews, and merges

Multi-compiler (GCC/Clang/MSVC) C++ code coverage report generator

CRANE-LLM: runtime-augmented crash prediction and diagnosis for ML notebooks

CrewAI tools that let agents discover APIs, MCP servers and CLIs through the Agent Nexus registry

CrewAI tool for the Council of AI GSPC measurement board (wraps csoai-gspc).

Shared core for CrewAI unified-memory StorageBackend implementations — build a Memory backend with five small primitives

Azure Cosmos DB StorageBackend for CrewAI unified Memory — hierarchical scopes, categories, metadata filters and native vector search (VectorDistance)

Amazon DynamoDB StorageBackend for CrewAI unified Memory — hierarchical scopes, categories, metadata filters and native vector search (SearchVectors)

Google Firestore StorageBackend for CrewAI unified Memory — hierarchical scopes, categories, metadata filters and native vector search (find_nearest)

PostgreSQL (pgvector) StorageBackend for CrewAI unified Memory — hierarchical scopes, categories, metadata filters and native vector search

Native CrewAI BaseTool to settle M2MCent x402 V2 Paywalls on Base L2 (1,062 Micro-Services, Vouch Grade A)

A CrewAI tool that pays per-request for SAGG LLM chat completions via the x402 protocol - no API key needed.

Verifiable AER-1 execution receipts for CrewAI agents. Every task event publishes a verifiable receipt at zambo.dev.

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

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

Gate a LangChain agent's tool calls with a CTRLRun policy, through wrap_tool_call.

Local phishing-detection agent for the Cybersecurity Browser Extension (Chrome)

Release gates for AI agent output: sources, baselines, statistics, stability, contradictions and adversarial review.

Agent Bricks CLI and AgentKit SDK for custom agents on Databricks

Gate LangChain tool calls and LangGraph nodes on a signed Decionis Decision Dossier.

Graph-backed context scratchpad for LangChain Deep Agents.

Docker Sandboxes (sbx) microVM sandbox backend for Deep Agents

Access Claude Code from your phone — full CLI sessions over Delta Chat

Production-grade, model-agnostic DevOps AI agent harness with policy, approval and audit enforcement outside the LLM.

The storage block family for dirigent: copy, read, write, and wait for an object at a URI.

Django reusable app: DRF-to-LangGraph agent bridge with long-term memory.

A reusable RAG toolkit for Django

Chunked pgvector embeddings for Django — the retrieval half of RAG.

DocsAgent - give AI agents instant, private access to your personal knowledge base. Zotero, Obsidian, and Apple Notes (macOS) MCP server (Python) over a resident native C++ search engine.

DocsAgent - give AI agents instant, private access to your personal knowledge base. Zotero MCP server (Python) over a resident native C++ search engine.

Multi-tenant, fail-closed Sphinx RAG extension for the doxtr ecosystem (dual-store ChromaDB knowledge base with security-classified xlinks).

Professional PDF watermarking service SDK

DRAGON A2A 协议客户端（Python）：官方 v1.0 卡面 + ARA 投影 + JSON-RPC 透传

DRAGON 领域框架契约面（Python SDK）：与 TS zod 正本逐值对齐的 pydantic 模型 + seam fixture 装载

DRAGON MCP 资源客户端（Python）：resources/list + resources/read（stdlib 传输）

Automated penetration testing report generator with command tracking and evidence.

OpenAI-compatible /v1/chat/completions bridge backed by the DeepSeek Harness (dsh) Python SDK.

Zero-dependency OpenAI-compatible proxy that adapts DeepSeek Harness (dsh) to any OpenAI-compatible endpoint (Socrates/LiteLLM/sglang/vLLM)

vLLM plugin for DuplexJev speech-decision models (Qwen3-ASR encoder + Ultravox-style projector).

Haystack integration for dynamodb

Local-first email monitoring agent: urgency, watchlist topics and sender analysis with a local web UI.

Task-delegation AI agent with multi-agent orchestration, research pipeline, and planning engine

Enterprise Agentic AI Framework SDK

Governance + orchestration framework wrapping the Anthropic Claude API for enterprise deployments

Reserved name. Envent AI does not publish this package to PyPI; it is installed from source.

Autonomous AI Agent compliance engine for EU Deforestation Regulation (EU 2023/1115)

e-volv Observer for Agents SDK for Python: agent runs, model calls and tool calls as spans the Observer rollup reads, with OpenAI, Anthropic and MCP wrappers.