Business agents

简约的插件化 Agent 框架

Headless Slack for AI agents. Channels, threads, DMs, reactions, and real-time events for multi-agent communication.

AAEP integration for agents built directly on the Anthropic Python SDK

MCP server and Claude-powered CLI for Mega.nz, Box, and OneDrive — one tool to manage all your cloud storage

Instrument LLM clients and emit usage events to Lago.

Drop-in Tessera integration for LangChain.js. One line of config routes your existing ChatOpenAI / ChatAnthropic / ChatMistralAI / ChatGroq / ChatCohere through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy.

The CopilotKit CLI scaffolds starter apps, connects project creation to a CopilotKit workspace through the Ops/Clerk platform, and manages local CLI authentication for CopilotKit Intelligence onboarding.

Agent-agnostic semantic memory for your vault. Turns notes into a queryable knowledge graph any MCP agent can search, log to, and reorganize.

Translate Django .po files automatically via LLM (Anthropic, Groq)

Your autonomous CLI AI engineer

Speak the Ollama API protocol — route requests to OpenAI, Gemini, Anthropic, AWS Bedrock, Azure, Groq, xAI, Mistral, DeepSeek, Together, Perplexity, Kimi, and any OpenAI-compatible server.

Python SDK and drop-in LLM guardrail for the SentraGuard backend (OpenAI / Anthropic / Gemini compatible).

Spec + reference implementation for vault-native, multi-runtime AI agents

A red-team benchmark for AI agents in financial workflows: measures regulatory-control bypass (sanctions evasion, threshold structuring, dual-approval defeat) and the efficacy of guardrails that try to stop it.

Reduce LLM API costs by up to 90% — prompt caching, smart routing, batch processing, and more

A thin, opinionated, local-first structured-output + logging layer over LiteLLM

Privacy-Preserving Phragmén Voting via Secure Multi-Party Computation

Generic async LLM gateway with concurrency, retries, and JSON helpers

One unified API for OpenAI, Anthropic, Google, DeepSeek, and xAI with simple fiat billing.

Toroidal semantic graph retrieval for measurable multi-hop RAG trade-offs.

LedgerProof adapter for the Anthropic Python SDK. Side-channel transparency receipts for EU AI Act Article 50.

Solo Founder OS agent #11 — monthly bill audit across Vercel / Anthropic / Supabase / OpenPanel / HyperDX. Flags underused SaaS + spend spikes.

Solo Founder OS agent #3 — draft personalized cold emails to investors (vc mode) or paying customers (customer mode), HITL queue + SMTP sender. Merged customer-outreach-agent in v0.9.0.

Fail-soft engine for agent workflows written in Python — drives an agent CLI through a checkpointed state machine, unattended for days.

TypeScript/JavaScript SDK for the AI Agent Runtime Monitor — cost guardrails, hallucination detection & audit trail

Lightweight client for FreeModel's Claude endpoint with retry logic, graceful error handling, and extended thinking support.

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

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

LiteLLM CustomLogger that adds RANKIGI cryptographic receipts to every model call routed through LiteLLM.

Longbridge review: compare features, pricing, use cases, access model, and alternatives for this Finance agent in 2026. Longbridge Skills v2.0 — 13 consolidated skills (down from 127) for Longbridge Securities.

CLI for reading and querying OFX 2.x (XML) financial files. Built for LLM/agent use: deterministic JSON output and a self-documenting --llm mode.

A modular TypeScript agent runtime with pluggable tools, skills, and LLM backends.

Cryptographic receipts for every AI agent action. Hash-chained, tamper-evident, regulator-ready.

Agent-centric, local-first observability: understand what your AI agents do, not just trace them.

Thread-based agents with typed streaming, tool-hide rules, branch compression, and optional Django persistence

Claude Agent SDK integration for Hindsight - persistent memory tools and hooks for Claude agents

SuperAgentX Policy Engine. Enterprise-grade AI Agent Governance Framework. Govern AI agents with policies, approvals, threat detection, cost controls, memory protection, PII, compliance protections and multi-agent security.

OpenJaw Agent — Autonomous desktop AI assistant for the terminal. Rich Ink TUI, 100+ tools, multi-channel bridges (Telegram, Feishu, Teams, WeChat). Standalone, no MCP server required.

A Model Context Protocol (MCP) server that enables AI assistants to automatically integrate the @divvi/referral-sdk into JavaScript/TypeScript blockchain applications.

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

The Angular AI agent chat UI: <chat>, headless primitives, interrupts, subagents, and generative UI on Signals.

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

Enforcement and audit layer for AI agents — argument-level tool firewall, trust scoring, tamper-evident audit log, and prompt-injection detection across the Anthropic & OpenAI SDKs, LangGraph, and MCP.

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. Bring your own model, local or hosted. `tai` command.

Agent core library: runtime, config, tools, providers, channels, db, cron, hooks. Lightweight, modular AI agent framework. Bring your own model, local or hosted.

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.