Business agents

Config-driven multi-agent debate council — add a reliability layer to any LLM pipeline

Typed SSE event protocol for AI agents — token, tool_use, thinking, progress, done

Core library for building AI agents with pluggable models and channels

DuckDB multi-org agent swarm with Spec Engine, 175+ SQL macros, meta-learning, MCP Apps, and smart extensions

Anthropic integration for Microsoft Agent Framework.

Microsoft Agent Framework Chroma.

Harness as a Service — production-grade multi-agent harness with LLM routing, paged context, hierarchical tracing, safety, and self-improvement

Adaptive threat intelligence for AI agent security — semantic memory, multi-turn escalation, output scanning, rate limiting, and prompt hardening.

CLI launcher for Cylestio Perimeter with default OpenAI and Anthropic configs

Three-layer persistent memory system (Markdown + ChromaDB vectors + NetworkX graph) for AI agents

A Python SDK for MCP tool integration with LLM providers

RAG MCP server: ChromaDB + sentence-transformers, exposes ingest/search/list/delete tools.

Intelligent rate limit handling for AI agents

Structured session checkpointing for AI agents — survive context limits, cost overruns, and session death

Compare baseline vs current agent runs and surface regressions as structured reasons: success loss, new errors, failed tool calls, output drift, step/latency/cost bloat.

Model-agnostic AI agent orchestration platform with unified interface for OpenAI, Anthropic, Google, xAI, Mistral and more

A Python library which wraps around Anthropic's low-level MCP client

Universal MCP server for any OpenAI-compatible LLM. Supports OpenAI and Anthropic API formats.

MCP server for agent reputation staking — trust through skin-in-the-game. Agents stake reputation as collateral; bad behavior gets slashed.

Synchronize agent files across providers

Rich threads for AI agents

A decentralized marketplace for agent capabilities - The Hands of AI Agents

LLM API 代理与日志追踪系统 - 透明观察智能体行为

LangChain integration for TrustAgents - protected document loaders, retrievers, and threat scanning

Standalone agent health monitor — detect loops, stuck states, thrash, and runaway costs in any AI agent workflow.

Server-side toolkit for the Claude Agent SDK over HTTP+SSE: session lifecycle, permission routing, SDK bridge, plus bundled FastAPI and Postgres adapters.

Go-to-market automation — Google Workspace, LinkedIn (Unipile), and Attio CRM

Batteries-included framework for building automation-focused AI agents with observability

Lightweight Python AI Agent Framework with Web UI

A simple LLM abstraction layer

Agenta is the open-source workspace for your agents. Build agents through chat, improve them with feedback, and share them with your team.

Record/replay testing for LLM agents - VCR.py but for LLM SDKs

Local-first runtime controls for Python LLM apps and agents: budget circuit breakers, PII/secrets redaction, tool-call policy checks, rate limits, and audit traces — in 2 lines, no hosted proxy.

Persistent memory and multi-agent communication — three transports (AgentTalk, Email, FTP), all open, all self-hostable

Management & Observability SDK for AI Agents

OpenTelemetry-based SDK for tracking AI agent usage and billing

LangChain callback handler for automatic usage tracking and billing with AgentBill

LangChain callback handler for automatic usage tracking and billing with AgentBill

Chaos proxy for testing LLM agent resilience — inject faults like latency, errors, and bad responses. Supports OpenAI, Anthropic, and MCP.

Official Python SDK for AgentBridge — connect AI agents to GitHub, Slack, Notion, Gmail and Google Drive through a single unified API.

Cost guardrails for LLM agent runs.

Evaluate agent system robustness through controlled, runtime, non-intrusive LLM API fault injection.

AI Agent Cost Governance — track, control, and optimize LLM spending

Python SDK for AgentCRM — agent-native contact & newsletter API

LangChain tools for AgentDraft — let LangChain, LangGraph, CrewAI, and AutoGen agents book calendars through the coordination layer without colliding.

Official Python SDK for AgentDyne — The Global Microagent Marketplace

A multi-agent asynchronous framework for swarm communication and task execution.

Python SDK for creating, managing, and deploying AI agents in Salesforce

Anthropic native LLM provider for AgentForge — Claude with caching, extended thinking, streaming

AWS Bedrock provider for AgentForge — Anthropic, Titan, Cohere on Bedrock

LiteLLM router-based LLM provider for AgentForge — 100+ underlying providers through one interface

Runtime protection and security monitoring for AI agents — The CrowdStrike for AI Agents

An asynchronous framework for building LLM-based multi-agent systems in Python, with a focus on trees of immutable messages and token streaming.

Intelligent LLM agent cost optimization runtime — per-run budget enforcement, semantic caching, model routing across 15 providers

Monitor and protect yourself with AI agent budget controls, approval workflows, and anomaly detection.

All terminology and labels used in AgentGuard materials are descriptive of software functionality only, not legal definitions or guarantees of compliance. Terms like receipt, audit log, evidence, audit trail, and attestation refer solely to cryptographically-signed records produced by the software. Full functional-use disclaimer in README.

AgentHub anthropic package

A lightweight agentic AI framework with MCP tool serving

A Python SDK for MCP tool integration with LLM providers

A framework for making agents more aware of their environment through explicit modeling of pre and post effects

Automatic context window management for AI agent SDKs

Autonomous folder exploration agent powered by Anthropic Claude

Compatibility alias package for bijux-canon-runtime. Preserves installs, imports, and the legacy agentic-flows PyPI package name and CLI command at the same synchronized version.

Production-Grade Agent Memory Framework for Agentic AI

Drop-in SDK to add an AI memory layer to any application. Works with OpenAI, Anthropic, Gemini, Claude.

Framework-agnostic memory layer for AI agents. Multi-signal retrieval, conflict detection, typed decay, checkpointing. Zero dependencies.

A Python SDK for MCP tool integration with LLM providers

Production-ready prompt management system with versioning, validation, and framework integrations for OpenAI, Anthropic, LangChain, and LiteLLM

Agentic Threat Hunting Framework - Memory and AI for threat hunters

Lightweight cost tracking for LLM pipelines and AI agents

AGENTICONTROL V0 MVP - Control plane for AI agents with synchronous blocking and asynchronous logging

Production-grade multi-agent framework with minimal dependencies

A package for building intelligent agents through OpenAI's API.

Production-grade, provider-agnostic Python framework for building agentic AI systems

Agentity MCP protocol plugin for Anthropic

LLM-neutral Python agent framework with built-in multi-channel messaging and document automation.

Cognitive continuity infrastructure for long-lived AI agents — cross-model state reconstruction, semantic recall, cognitive compression

Python SDK for AgentKeys — proxy API calls through a secure credential vault

Python SDK for AgentKeys — proxy API calls through a secure credential vault

Profile AI agents by intercepting LLM API traffic through a local MITM proxy

Lightweight A2A + MCP single-process agent framework

A small, focused library for building Claude-powered agents in Python.

Trace AI agent execution — LLM calls, tool calls, costs and latency

AgentLoop SDK — middleware that turns human corrections into searchable memory for your agent.

Drop-in Anthropic SDK wrapper for AgentLoop — adds memory retrieval and turn logging to messages.create calls. Supports streaming.

AgentMake AI MCP Servers - Easy setup of MCP servers running AgentMake AI agentic components.

Claude Agent SDK adapter for AgentMark - integrate AgentMark prompts with Claude Agent SDK

Claude Agent SDK adapter for AgentMark - integrate AgentMark prompts with Claude Agent SDK

Python SDK for agentmb — local Chromium runtime daemon for AI agents

A decentralized marketplace for agent capabilities - The Hands of AI Agents

Notarize, govern, and audit AI agents — cryptographic seal, runtime guard, and EU AI Act compliance docs

AI Reliability Engineering for LLM Agents - Monitor hallucinations, latency, and throughput

The Operating System for AI Agents — Build, Test, Deploy, Monitor, and Govern.

AgentOS - TGSC

Lightweight observability for AI agents — track costs, tokens, and traces

Zero-config agent observability SDK — auto-captures LLM calls, costs, and traces

Lightweight AI incident detection. Catch cost spikes, latency anomalies, and prompt bloat before they hit your users.

OpenAI- and Anthropic-compatible API server that routes through agent CLIs

A Python SDK for MCP tool integration with LLM providers

Safety controls for AI agents — budgets, approvals, rate limits, and audit logs