Business agents

Agentic MCP - Three-layer progressive disclosure for MCP servers with Socket daemon

Redis and Postgres adapters for @infra-tools/agentic-ui-server's ThreadStateStore interface — multi-pod-safe thread state for production deployments.

Agentic commerce plugin for Medusa v2 — adds UCP and ACP protocol support, enabling AI agents to browse, checkout, and pay at any Medusa storefront.

Nuro CLI. Agentic finance, orchestrated from your terminal.

Agentic chart-of-accounts categorisation for bank transactions, powered by Claude. Production patterns: Zod-validated structured outputs, prompt caching, multi-provider abstraction, evaluation harness.

TypeScript SDK for the Synchronity agentic commerce infrastructure

Comprehensive security guards for LLM-powered and agentic AI applications - 35 guards covering OWASP Top 10 for LLMs 2025, Agentic Applications 2026, and MCP Security. All guards accessible via unified TrustGuard facade. Features prompt injection (PAP/per

Agentic memory manager. Best used with skill: npx skills add meharajM/agent-loop-mcp

Cogitum — sovereign agentic CLI. Textual TUI, multi-provider LLM mesh, persistent sessions, skills, MCP, Telegram gateway. Cross-platform npm launcher.

Stablecoin payment handler for Saleor agentic commerce. Enables AI agents to pay with USDC via Finance District Prism and x402/EIP-3009 signed transfers.

Strategy Agent bridge — A2A protocol integration for LangGraph strategy-agent (37 financial analysis skills)

Wrap LangChain/LangGraph tools with Zehrava Gate governance — deterministic policy enforcement before any tool executes

Strategy Agent bridge — A2A protocol integration for LangGraph strategy-agent (37 financial analysis skills)

Server llms-txt documentation over MCP (Node.js/TypeScript)

Circuit breaker for AI agents — pick budget-guard, loop-killer or worth-it mode and stop runaway token spend, stuck agents or budget overruns in one wrapper. Adapters for LangChain, OpenAI Agents SDK, Claude Agent SDK, Vercel AI SDK and LangGraph Platform

Visual canvas for AI conversations — branch, explore in parallel, merge insights

MCP Server Infrastructure Platform with 7 financial tools

MCP Server Infrastructure Platform with 7 financial tools

TypeScript SDK shim for My Compliance Center. Drop-in replacement for @anthropic-ai/sdk, openai, and @aws-sdk/client-bedrock-runtime with unavoidable governance enforcement.

A lightweight, TypeScript-based framework for building graph-based workflows and AI agents

MCP server for Cream — the universal payment control plane for AI agents. Exposes payment initiation, policy inspection, audit queries, virtual card issuance, and provider health through MCP tools, resources, and prompts. Translates MCP calls into the Cre

Lombard Action Provider for Coinbase AgentKit - stake BTC, mint LBTC, and interact with DeFi via AI agents

Deterministic tool orchestration for LLM/SLM flows with policy-gated parsing.

AgentAssert Type-C SDK wrapper — wrap(Anthropic(), 'contract.yaml') to enforce behavioral contracts on direct API clients.

Official LangChain / LangGraph integration for Thrindex — persistent semantic memory for AI agents.

America's Law Graph lets you search through every US law from all 50 states and Washington D.C. It combines over half a million statute sections into one easy-t

A lightweight, provider-agnostic agent loop for building LLM agents.

**sofIA** is an agentic CLI that guides facilitators through a structured AI Discovery Workshop — from understanding a business and brainstorming AI use cases, all the way to generating a working proof-of-concept. It reimagines two Microsoft open-source p

MCP server for SUMO traffic simulation: orchestrate networks, trips, simulations, and analysis from LLM agents.

Planetary Agents MCP server — converse with historical-figure personas, council-feed threads, and culinary debates from alchm.kitchen.

A simple, unified interface for RAG across multiple vector store backends (txtai, Chroma, Qdrant, LightRAG)

LangChain integration for Nomad headless browser engine — 700× cheaper than Chrome

Drop-in, compliance-instrumented wrapper around the official Anthropic Python SDK.

Automate sales outreach with AI to find and contact the right leads.

本地统一 LLM 模型代理工具 — 多协议路由、协议互转、流式 SSE 转换、token 统计、协议抓包调试

Framework for building Model Context Protocol (MCP) servers in Typescript

LLM client layer for the Lexigram Framework — OpenAI, Anthropic, Ollama, Cohere, Groq, Mistral

Route prompts to the right LLM by complexity. Supports Groq, OpenAI, Anthropic. Save cost, keep quality.

Decorator-based LLM-native typed Python functions — declare the signature and docstring; the LLM runs the body.

Production-ready RAG with near-zero hallucination. Pluggable providers (OpenAI, Anthropic, Gemini, OpenRouter, Azure, Voyage, ...), graph + agentic + multilingual strategies, a FastAPI server with a bundled React UI, and one-click publishing of a configured setup as a public ask-only assistant.

Eight-layer middleware guardrail pipeline for LLM-powered personal finance applications

Universal Python LLM Provider Abstraction Library

pytest-compatible test harness for AI agents — deterministic record & replay for Anthropic Claude

Make your AI agent evolve automatically through iterative harness optimization.

Government tender search for AI agents. UK, EU, US contracts with AI bid scoring. BID/SKIP verdict with deadline and value in one call.

Streaming ReAct agent in typescript with multiple LLM providers

An MCP server that exposes a MeshCore node — and the mesh reachable through it — as a clean, high-signal interface for AI agents and tools. Built on @dpup/meshcore-ts.

Full unofficial agentic Infomaniak MCP server — guided automation of web hosting, mail, kDrive, domains and DNS

Security operations copiloto for threat intelligence, incident response, and agentic investigation

LangGraph adapter for @threadplane/chat — Angular bindings for LangGraph Platform.

This README is the public trust contract for `@threadplane/*` telemetry. It is linked from package install notices and should stay aligned with implementation.

Local-first, MCP-native multi-agent platform — job tracker + daily briefing for software engineers, with tracing, evals, and budgets.

MongoDB Atlas-backed thread/session persistence + semantic/episodic vector memory for VRSEN Agency Swarm.

Run automated tests against Salesforce Agentforce agents (External + Internal Copilot) and score them into evidence — fully local, privacy-first, no API key required.

Own your agent as a neutral folder; audit its portability, compile it to provider formats (Anthropic YAML / AWS Bedrock AgentCore / Google ADK), and deploy it live (Anthropic, AWS Bedrock AgentCore Harness, Google Agent Engine). Own the definition, rent the runtime.

A plugin for Enthusiast that provides an Anthropic connector.

Self-hosted observability dashboard for agentic flows — every LLM turn, tool call, and failure captured

ToolHive review: compare features, pricing, use cases, access model, and alternatives for this Legal agent in 2026. Productivity tool, Legal, Compliance

Headless LLM-driven trading agent for Shell Finance — a confidential dark pool on Sui. Posts Seal-encrypted IOIs to Walrus, polls Nitro-enclave match proposals, LLM picks IOI terms and accept/reject decisions, settles atomically peer-to-peer on Sui. Multi

Framework adapters for mosadd. Subpath exports: @mosadd/ai/vercel, @mosadd/ai/langchain, @mosadd/ai/openai, @mosadd/ai/anthropic. Single package, atomic releases (Stripe Agent Toolkit pattern).

MCP server for e2a — email for AI agents

Zero-config drop-in client wrapper and proxy to optimize and compress prompts for OpenAI and Anthropic Claude.

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.

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 runner for YAML-defined agent workflows — drives the Claude CLI through a workflow graph 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.