Python agents

Ergonomic agent harness on top of agentharness-core: Agent, @tool, and testable, replayable runs. Imports as `agentharness`.

Framework-agnostic agent orchestration with A2A, MCP, runtime adapters, and vendor-fabric tools

Agentic RAG over consent-gated Web3 documentation — search and answer developer questions from Ethereum, Solidity, and ecosystem docs.

An MCP which adds terminal capabilities to an agent

An MCP which adds terminal capabilities to an agent

Profile, analyze, and optimize token consumption in LLM-powered applications and agentic workflows.

AgentLens Python SDK — zero-overhead observability for AI agents

Measure the real-world error rate and dollar cost of an AI agent's decisions. OpenTelemetry-native.

Convert LangDock agent exports into Claude skills and manage them locally.

Build inspectable AI agents with ordinary Python functions and no workflow DSL.

LLM Observability and Evaluation SDK

Verifier for AgentOracle composed envelopes (RFC 8785 JCS + Ed25519). Canonicalization is byte-identical to the production Node canonicalizer.

Agent Operating System — Production-ready multi-model agent framework with Tool-Using Agent, LLM Provider abstraction (OpenAI/DeepSeek/Anthropic), Function Calling, streaming, retry, checkpoint/resume, A2A protocol, swarm coordination, and comprehensive observability.

A sequential crew of AI agents that clean up your codebase.

Agent Knowledge Compiler — one source, many AI targets

Python SDK for the AgentPay task escrow and settlement protocol on Celo.

Risk guardrails for AI trading agents. Your agent proposes; your policy decides.

Static security scanner for agentic AI configuration: settings, permissions, hooks, MCP servers, agents, skills, and steering files (Checkov for AI agent stacks).

Python SDK for AgentsCoin — give your AI agent its own on-chain wallet: create wallet, send, create + trade tokens.

Static security scanner for AI coding agents and MCP configurations

Make sense of what your AI agents did — local-first, MCP-native observability, trace replay & trajectory diff.

AI Agent Runtime Security Sandbox

Deterministic snapshot testing harness for AI agents

Reserved name placeholder. No functionality.

Framework-agnostic message reducer for AI agent state management. Works with LangGraph, CrewAI, and plain dicts.

Time-travel debugger and branch explorer for LangGraph AI agents. Capture execution traces, inspect LLM and tool calls, and branch from any point with overridden outputs.

System-level performance benchmark suite for agentic AI workloads (pre-release)

AI Agent security guard - policy engine for LLM tool calls

Типизированный async-клиент Agentum Cloud (/v1): загрузка документов, поиск и RAG-вопросы по вашим файлам.

Open-source observability, cost tracking, and governance for AI agents

Python client for the AgentWorth governance gate (REST over the HTTP ingress)

An open-source, provider-agnostic agentic framework + interactive project scaffolder for LangChain and CrewAI. Pick your LLM provider, agents, RAG, memory, MCP tools and skills — generate a ready-to-run uv project.

Keyless MCP security shield: wrap any MCP server so every tools/call is screened and recorded; set the posture to enforce and a blocked call comes back as coaching your agent recovers from. Launcher for agentx-security-sdk.

Тонкий harness-фреймворк для AI-агентов: сменный провайдер рантайма (API/Claude Code/Codex), middleware-pipeline и слой skills/MCP.

Tamper-evident, third-party-verifiable receipts for AI agent / MCP tool calls

AI Agent Builder - Templates and tools for building AI agents

Small metadata and URL helpers for AI Agent Skills, a curated Claude, Codex, and AI agent skills directory.

Fetch Akeyless secrets at runtime on AWS Bedrock AgentCore using cloud identity authentication

Carry an AlgoVoi keystone decision into an AutoGen conversation: a recomputable execution_ref under algovoi.keystone.*, verifiable offline

Carry an AlgoVoi keystone decision into a crewAI run: a recomputable execution_ref under algovoi.keystone.*, verifiable offline

Carry an AlgoVoi keystone decision into a LangChain run trace: a recomputable execution_ref under algovoi.keystone.*, verifiable offline

Alibaba Cloud RealTranslationAgent (20260622) SDK Library for Python

Reserved name placeholder. No functionality.

Name reserved for Alvarez Agent. Real releases will appear here.

Ant Chain IOTAGENT SDK Library for Python

Git for LLM context. Snapshot a dying session, brief the next model in 30 seconds.

LangGraph controller and actions for AOA.

Prepare Arabic (and mixed Arabic/English) documents for RAG and search: normalization, sentence-aware chunking, and a provider-agnostic vector index.

Standalone offline verifier for Open Decision Receipts (ODR) -- check schema, JCS canonical digest, Ed25519 signature, and hash-chain linkage with no Aragora install or account.

AutoGen tools for Signatrust — cryptographically signed, tamper-evident AI Decision Receipts.

Governance patterns for autonomous AI agents in regulated banking

Bark notification hooks for Codex, Claude Code, and OpenClaw agents.

MCP server providing Base L2 DeFi tools for AI agents

Python SDK for BaseCodeAgent — discoverable AI agent services on Base with x402 payments

Batch processing for LLM APIs - CSV/JSONL in, processed out. With retries, rate limiting, and cost tracking.

Quality gates and retry loops for Amazon Bedrock Converse.

Bench adapter for LangChain — auto-instrument every chain, agent, and LLM call.

Long-term memory tier for AI agents backed by Valkey Search: semantic recall with recency/importance ranking, scoped capacity eviction, and consolidation. Pairs with @betterdb/agent-cache.

x402 payment SDK for billmyagent — auto-pays HTTP 402 challenges with an eth-account signer and gates your own endpoints (FastAPI/Flask)

A pragmatic BitChat CLI for public BLE chat

CrewAI tools for Blacksands Bursar

LangChain tools for Blacksands Bursar

MCP server for Blender 3D — expose Blender modeling tools via Model Context Protocol

Host-agnostic LLM agent execution on top of the OpenAI Agents SDK: model fallback, streaming, structured-output extraction, self-correction, and tracing — behind a small injected provider seam.

Run your coding agent in a bubble.

Retrieval-only MCP server over the indexed React documentation, with a prebuilt index downloaded on first run.

Renamed to neosyn-fpga-mcp. This package only installs it.

A chunk-source-agnostic evaluation harness for RAG chunking strategies

Visualize AI agent step progress in the terminal

Local session-history browser, token/cost analytics, and productivity insights for Claude Code.

A zero-dependency Python module for inspecting and converting Claude Code session files (.jsonl) into the messages format expected by Hugging Face Transformers.

Cost-aware model routing for the Claude API — reference implementation with a Claude Code subagent hook

Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file.

Windows tray app, overlay and dashboard for Claude plan limits (5-hour & weekly), with pace forecasts

Standalone, dependency-light verifier for CloakLLM audit artifacts -- verify hash chains, Ed25519 signatures, key provenance, RFC 3161 timestamps, and compliance reports WITHOUT the full SDK or trusting CloakLLM's code.

Cloud-Dog agent strategy primitives (PS-96) + prompt-engineering (D5) + per-LLM format adapters (W28M-1601): codeact/react/reflexion arch + adapters reconciled (0.3.2)

PS-50 LLM Interfaces for Cloud-Dog services

Cloud-Dog AI platform storage library — storage backends plus PS-94 transfer helpers

AgentWatch SDK — AI agent governance, audit, and policy enforcement

Local-first retrieval engine for technical documentation.

Python SDK for TNG — direct OHTTP encryption for confidential AI

Coinbase AgentKit action provider for the Legends of Champz AI Agent Arena on Base L2

A minimal Agent framework.

Add your description here

EU AI Act compliance scanner for AI projects

Conductor Agent SDK — durable, scalable, observable AI agents

Typed declarative contracts for AI agent systems.

一款纯净的自主 Agent 系统。

Recomputable verification adapter for CrewAI — 6-dim verification, drift detection, and verified failover

AutoGen integration for CortexDB — long-term memory for AI agent conversations

LangChain integration for CortexDB — long-term memory for AI systems

High Performance Vector Engine for RAG using AVX2 SIMD and Zero-copy

Python SDK for the Couchbase Agent Memory API

Reference architecture for AI agent governance in commercial real estate operations — Autonomy Ladder™ patterns, MIT-licensed.

Pre-built CrewAI skills for reliable web automation: form filling, data extraction, multi-step navigation, auth handling, and anti-detection. Integrates browser-use/Playwright. Skills include LinkedIn scraping, price monitoring, job automation, competitor research, and lead generation.

Pre-built, production-ready CrewAI skills for common enterprise integrations: REST/GraphQL API clients with auth handling, web scraping with anti-bot bypass, email parsing (Gmail/Outlook), document processing (PDF/Excel/Word), data validation pipelines, and database connectors (PostgreSQL, MongoDB, Snowflake). Each skill includes error handling, retries, rate limiting, and structured output schemas.

Mimir long-term memory as CrewAI tools — local-first, encrypted, persistent memory the agent can explicitly call.

CrewAI tool for SibFly — measured ground motion (subsidence & uplift) per US address, from NASA Sentinel-1 InSAR

CrewAI tools for Signatrust — cryptographically signed, tamper-evident AI Decision Receipts.