Business agents

Framework-agnostic multi-agent task delegation - in-memory bus, typed tasks, LLM coordinator, dead-letter queue

Drop-in agent chat UI for Angular 20+. Headless UI primitives plus opinionated compositions that read a runtime-neutral `Agent` contract — ship a production chat surface in days without coupling to a specific backend.

LangChain callback handler for NeBeso AI cost tracking

LlamaIndex callback handler for NeBeso AI cost tracking

Cache-optimized LLM conversation history management with static/dynamic system prompts, transition modes, and compaction hooks.

Three-tier memory with trust-aware context ledger for multi-agent LLM systems

Upwex review: compare features, pricing, use cases, access model, and alternatives for this Lead Generation agent in 2026. AI-powered Chrome extension for Upwork freelancers to manage proposals and clients.

Framework-free workflow engine for ccaas. Cascade context, trigger registry, engine + state-change pipeline + types. Pairs with @kedge-agentic/workflow-nest (NestJS adapter) and @kedge-agentic/workflow-client (HTTP client) to form a three-sibling family.

High-ticket business builder — AI agent pipeline CLI

Security observability layer for LangGraph and Anthropic SDK AI agents

Anthropic Claude SDK with OmegaEngine governance - AI safety and compliance

Lookup capabilities (context window, modalities, features) of various LLM models offline.

A high-throughput and memory-efficient inference and serving engine for LLMs

Anthropic native provider for CrewAI TypeScript.

Replay recorded LLM API traffic against a candidate model: cross-provider migration & regression reports (OpenAI/Anthropic/Gemini/Mistral) with scoring, cost and latency, built on httpx record/replay

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

HonorNet agent presentation client (MCP-first) — a protocol shim that mints proofs and presents three-part ADR-009 bundles. It decides nothing (hard rule 3).

Automatic model routing and deprecation handling for OpenAI, Anthropic, and Google Gemini

Parse streaming SSE responses from OpenAI, Anthropic, Gemini and OpenAI-compatible providers into one unified event format. Text, reasoning and tool-call deltas. Zero dependencies.

Browser automation CLI for AI agents

n8n community node for routing LLM requests through Pay-i proxy with cost tracking and budget enforcement

Framework-agnostic browser-control surface for LLM agents. Bounded tool API over Playwright, with egress allow-list, vault $ref expansion, output sanitiser, and always-HITL gates. No dependency on any specific agent framework.

YEScale nodes for n8n

A premium TypeScript client wrapper for the Loopers AI budget & rate-limit proxy.

TypeScript SDK for autonomous agent sessions across Anthropic, DeepSeek, OpenAI, Gemini, Mistral, OpenRouter, and Doubao.

Tailored AI CLI — lightweight, modular AI agent framework optimized for local LLMs. `tai` command.

Agent core library: runtime, config, tools, providers, channels, db, cron, hooks. Lightweight, modular AI agent framework optimized for local LLMs.

Embeddable agentic chat widget powered by Anthropic

轻量级个人助手 Agent CLI — 集三大开源项目设计思想之大成的融合实现

LangChain tools for the HonorNet agent presentation client — a protocol shim that mints proofs and presents three-part ADR-009 bundles. It decides nothing (hard rule 3).

OpenAI-Agents tools for the HonorNet agent presentation client — a protocol shim that mints proofs and presents three-part ADR-009 bundles. It decides nothing (hard rule 3).

IRIS governance for Anthropic Claude — Cedar policy on every API call

Fetch, normalise, snapshot, and diff official LLM API token pricing.

Salesforce REST/SOQL/Bulk API 2.0 connector + MCP Server + A2A Server for Agentic AI!

AgentLedger Python SDK — track, attribute, and govern AI agent spend across OpenAI, Anthropic, and Gemini.

Sync Made Easy review: compare features, pricing, use cases, access model, and alternatives for this Ecommerce agent in 2026. Sync your Shopify with Salesforce seamlessly and sell faster!

Record/replay LLM & agent API calls for fast, free, deterministic tests. In-process recorder + optional gateway shim.

Cairn — an AI that walks your system and leaves a trail of tests. Autonomous QA agent (UI today; API/unit/docs planned) on LangGraph + Claude/OpenRouter, with self-improvement via Langfuse.

Verigent trust verification for the Claude Agent SDK

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

Validate API keys for OpenAI, Anthropic, Google Gemini, Groq, Mistral, OpenRouter, Cohere, DeepSeek, Together, Fireworks, xAI, and Perplexity. Zero dependencies. CLI + library.

Static, deterministic LLM prompt/payload compression that cuts input tokens 30-90% with zero extra model calls.

Python SDK for Loupe — observability for LLM apps (latency, tokens, cost, errors).

A lightweight framework for multi-AI-agent cohabitation — where AI agents live together, share memory, and collaborate like roommates. 🏠🤖

Provider-agnostic agent harness — memory, tools, sub-agents, and observability wrapped around any LLM.

MCP server for Site-Shot — give Claude and other AI agents the ability to take website screenshots (real Chromium, full-page, country proxies, automatic ad & cookie-banner removal).

Verify the merchant before your AI agent pays. A pre-pay storefront-legitimacy check (address + company-register + domain-binding + sanctions) for LangChain, CrewAI, Anthropic computer-use, or any MCP agent.

Anthropic tool_use governance middleware for Aegis ACP

LangChain governance middleware for Aegis ACP (maintenance-only — Anthropic SDK is the active hero)

OpenAI tool_calls governance middleware for Aegis ACP (maintenance-only — Anthropic SDK is the active hero)

Shared core for OpenClaw and Hermes Agent game skills — IM-native Three Kingdoms strategy

LangChain and LangGraph integration for the Mnemosyne memory substrate. BaseChatMessageHistory, BaseMemory, and BaseRetriever adapters with hybrid BM25+vector recall, per-session thread tracking, automatic redaction, TTL support.

Drop-in observability for LLM calls — cost, tokens, latency, errors via OpenTelemetry GenAI conventions.

Lightweight identity, auth, and audit layer for AI agent SDKs (OpenAI, Anthropic)

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

OpenAI-compatible client + agent for Cana Apps — Bearer auth (App API key or short-lived browser JWT with auto-refresh), server-hosted MCP federation, streaming, typed structured output. Node 18+, Bun, Deno, Workers, browsers.

TypeScript client library for connecting to Civic Hub and exposing MCP tools to AI SDKs

Multi-agent decision-making framework with flat inference and a 4-layer creative pipeline

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

Production LLM calls. Just the three lines. Reliability, native caching, and reversible context compression on by default.

LeviathanTalon: hierarchical Kabbalistic multi-agent swarm orchestrator. 2,832 concurrent agents at full scale.

A tiny, dependency-free tool belt for LLMs: token counting, cost estimation, retries, prompt templates, and text chunking.

pprof for your LLM context - see where every token and dollar goes.

AutoGen v0.4 MemoryStore adapter for the Mnemosyne memory substrate. Implements the MemoryStore protocol with per-agent container scoping, hybrid BM25+vector recall, async support for high-throughput multi-agent runs.

Ontology-guided knowledge graphs and graph-grounded RAG for document intelligence

Multi-provider AI agent CLI supporting Ollama, Bedrock, OpenRouter, OpenAI, Meta, Gemini, xAI, Cloudflare, and Anthropic

Cross-project LLM agent runtime for Dragonflow — loads agent rows from a per-project `agents` Supabase table and invokes Anthropic / Google / OpenAI models against the v0.1+ invocation contract.

E2E parity validator for site migrations. Compares prod vs cand and reports UI, functional, SEO, visual, and Web Vitals deltas with an LLM-ranked HTML report.

Vigil — a defensive-cyber terminal agent for Computer Network Defense. Asset discovery, vulnerability assessment, hardening, detection engineering, threat hunting, incident response — on the infrastructure you defend.

A headless, multi-provider AI agent harness. One install gives you the `cortex` CLI and HTTP server: npm i -g nexus-cortex.

Sanctum Runtime SDK — the runtime trust boundary for autonomous systems. Signed action tokens, blast-radius scoring, source-trust classification (indirect-prompt-injection defense), dual-approver + auto-escalate, policy replay, SOC2 + NIST AI RMF evidence

AWS Bedrock Agents governance middleware for Aegis ACP (maintenance-only — Anthropic SDK is the active hero)

One-line spending control for AI agents. @budget(max_usd=10.00) decorator for LLM APIs and x402 payments.

First-Class Hermes Tool Agent — Offline ReAct agent with dual memory (episodic + semantic), skill learning, and daemon mode

LangChain integration for rezunate-llm-sdk

Shrink LLM context windows by removing noise, redundancy, and long-tail detail — without losing signal.

MothRAG: adaptive multi-arm subset routing for multi-hop retrieval-augmented generation — high-level Python API with auto-defaults.

Token-efficient prompting and agentic workflows for Claude

A small, framework-agnostic LLM-in-a-loop primitive: zod-validated tool registry, 5 independent stop conditions (steps / tool-calls / wallclock / tokens / cost), and trace/budget output. SDK-agnostic via a single AgentStepFn seam.

OpenAI / Anthropic tool-calling adapter for cdr-kit — JSON-Schema tools[] + a dispatch router.

Heal broken Vercel AI SDK message arrays before they hit the provider. Fixes orphaned tool calls, missing reasoning signatures, invalid tool names, and other provider rejections.

一个用于测试的 Mock LLM 服务器，支持 OpenAI、Anthropic 和 Responses API 格式

ESLint for your LLM prompts — catch prompt-injection risks, missing token limits, and prompt anti-patterns before you ship.

Paybyrd integration for a claude AI agent

A protocol and reference implementation for user-customizable web app interfaces. Apps declare schemas, actions, and primitive components. Users (via an LLM agent) compose those primitives into custom views, parameterized by a theme token vocabulary. The

Logging and tracing layer for AgentsKit agents.

Coinbase AgentKit ActionProvider for trading Thetanuts options on Base — for autonomous backend agents that own their own wallet (CDP, viem, Privy, server wallets).

Unified LLM API with automatic model discovery and provider configuration

Agente de navegador autónomo con IA (Claude). Abre Chrome o Firefox reales, lee la página y la opera con una sola instrucción en lenguaje natural. Incluye truco CDP anti-Cloudflare.

Lightweight Python client for the Agentic Trading Lab REST API (LLM-powered trading agents, backtests, paper trading).

FreshRSS API + MCP Server + A2A Server

A pre-spend GATE + learning advisor for LLM API cost: caps every call, prices from a verified table, and learns the cheapest config that keeps quality.

MemGPT memory architecture as a Python sidecar for the openclaw-memgpt plugin. Includes Anthropic/Claude compatibility patches against the original MemGPT (Apache 2.0).

Qode — LLM provider abstraction layer (Anthropic, OpenAI, Google, Ollama, etc.)

Access AI models, email services, and project thumbnail capture through vly.ai and freebuff.com without managing multiple API keys or accounts

Papaya AI agent trace capture SDK for production apps.

A small-but-complete agent harness: ReAct loop, tool injection, three-tier memory, restricted-expression panels. Zero heavy deps.

The language-agnostic governance-gate sidecar — govern a non-MCP agent runtime (LangGraph, CrewAI, AutoGen) by remoting each native tool call through the Action Kernel over a thin NDJSON-RPC seam. The reusable spine of Lodestar's runtime-adapter epic.

AgentMetrics observability integration for Claude Managed Agents

Memory-backed autonomous agent with a Docker membrane, a Slack/Discord cockpit, and capability graduation.