Business agents

Integra Agentic Terms — the buyer-side verify-before-sign gate for agentic purchases. Fetches the terms a seller advertised, recomputes the fingerprint, and halts before any signing key is invoked if they disagree. Works against any seller.

Places an LCP reference into an ACP (Agentic Commerce Protocol) message, and reads it back.

Agentic video generation with byte-stable local rendering, scene-linked narration, and reviewed capability plugins.

A firewall for AI agents: block prompt injection, guard tool calls, redact PII/secrets.

Lightweight Python agent framework. Config → agents → run.

Stateful simulation and fault-injection testing for AI agents that take actions through tools.

Log in to Claude.ai without touching your inbox: magic links auto-open in the right browser via IMAP IDLE

An interface for SSH agent socket providers, which expose an abstract communication channel for an SSH agent to derivepassphrase.

Anthropic target and judges for digline: prompt file in, priced Response out.

FinanceGPT Intelligence Cloud API and MCP client

LangChain retriever integration for Hacker News — search stories, fetch the front page, and retrieve full comment threads without API keys.

Harness, loop and graph engineering for production AI agents.

Gate every LangChain agent action through Qerexa runtime trust enforcement.

The complete RAG evaluation library. Scores, diagnoses, and domain-aware.

AI-powered reconciliation agent for finance.

High-throughput LLM Gateway and Circuit Breaker for distributed AI agents

LangChain integration for SafePrompt — prompt-injection detection as a callback handler. Validates every prompt flowing through a chain before it reaches the LLM.

Retrieval-augmented generation, built around your scientific domain.

Run bigger LLMs on smaller GPUs through intelligent, asynchronous layer streaming.

OpenTelemetry Anthropic instrumentation

A unified interface to all major LLM providers with system certificate and async support

AgentWorks AI Front Desk review: compare features, pricing, use cases, access model, and alternatives for this Customer Service agent in 2026. 24/7 AI receptionist and CRM for 26 service industries.

Veryfront first-party extension package for ext-llm-anthropic

One permanent AI agent that builds, runs and retires other agents per task.

Anthropic (Claude) LLM client for AI-Parrot (parrot.clients.anthropic)

Schalter und Protokoll fuer die digitalen Mitarbeiter: Aufgaben zur Laufzeit an- und abschalten, Vorschlaege vermerken und ihre Trefferquote messen.

A local CLI and MCP server for talking to configured AI models through LiteLLM.

Route a CTRLRun APPROVE through LangGraph's own interrupt().

Route a CTRLRun APPROVE through the OpenAI Agents SDK's tool-approval interruption.

Register Anthropic-protocol-compatible providers as first-class llm models

Official Anthropic Messages SDK adapter for PurrA

Durable, fully-traced orchestrator that triggers any registered Pydantic AI agent from any channel and delivers results back through one uniform Trigger/Notifier interface.

Autonomous Zero-Vector Memory Framework for AI Agents with Biological REM Consolidation (Gemini, Anthropic, OpenAI-compatible, xAI)

AI-assisted SOC alert triage and incident analysis toolkit

Real Estate AI Operating System for new realtors — automate listings, CMA prep, lead follow-up, and open-house marketing. By Double Helix Construction.

Reusable model provider adapters and streaming runtime from OpenClaw

Unified LLM API with automatic model discovery and provider configuration

MCP server for AgentPay — autonomous agent infrastructure for payments, API key vaulting, and governed mandates. One OTP vaults credentials so agents never handle raw API keys. Agents spend money within user-defined limits. Works with Claude, GPT-4o, and

assistant-ui thread binding for statewire backends

AI CLI for software engineering — chat with OpenAI, Anthropic, Google, Groq, Together AI and custom endpoints

ETTORE - Advanced AI CLI Assistant

A multi-agent runtime for Node.js: agents, models, tools, skills, memory and an append-only trajectory.

Anthropic Claude adapter for agentic-auto-correct.

Local multi-agent collaboration runtime — shared threads, roles, HITL, model-agnostic backends.

Signed, verifiable receipts for AI agent tool calls, from Python, through the agent-custody sidecar

Conduit — lightweight AI driver for OpenAI-compatible, Ollama, Anthropic, Gemini (Python)

Language-agnostic LLM cost metering via HTTP proxy — track spend per customer and feature

RAG pipeline sederhana pakai OpenRouter dan ChromaDB

Geodd provides fast, steady AI model hosting through serverless inference and dedicated GPUs. It supports OpenAI-compatible tools, regional deployment, usage tr

May 17–18, 2027 in Midtown, New York City. Reserve your ticket now — or subscribe for speaker reveals, agenda drops, and sponsorship openings as they land.

Universal Anthropic adapter and provider plugin for ai-agent-sdk

An AI agent command-line interface

Universal Anthropic Messages wire schema, serializer, translator, and dialect for ai-agent-sdk

Model Context Protocol adapter for ai-agent-context. Exposes the repository knowledge graph to MCP clients over stdio. Contains no business logic of its own.

Conto SDK for AI agent payment authorization

Create and publish AI agent work through OWL Compose Hosted

Tenant and permission isolation for LLM agent tool calls: a principal context on AsyncLocalStorage, a guard that scopes every call and audits it, and a test kit that proves no tool escaped.

Record every boundary an LLM agent crosses: withRewind, the recorder, the redactor, and the stores.

A composable agent loop that wires Armorer and Conversationalist into the standard agentic cycle. Includes provider subpaths for Anthropic, OpenAI, and Gemini (dynamically imported — zero-SDK-if-unused).

Embed Archstone capabilities directly in your own agent loop: typed tool definitions for Anthropic, OpenAI, Gemini and plain JSON Schema, plus fail-closed execution over a compiled IR — no MCP server process required.

Compress LLM tool output, reduce context tokens, and recover lossy originals from a local stash.

Official Node.js/TypeScript SDK for Moda — the continual learning layer for AI agents. Automatic conversation threading and OpenTelemetry-native tracing.

A lightweight runtime that unifies 110+ AI providers behind a single, OpenAI-compatible API.

Unified LLM API with automatic model discovery and provider configuration

The agent loop, tool execution, context management and permissions. No frontend, no transport.

通用对话式 Agent 执行引擎：OpenAI Responses / Anthropic Messages 双协议 + Agent loop + 文件工具 + 可选 REST/SSE 服务层

ZUI UI for AI-assisted enterprise apps: assistant dock, thread, streaming markdown, tool calls, approvals, diff review, structured output, citations, provider adapters

Browser transport implementations for Model Context Protocol (MCP) - postMessage, Chrome extension messaging, and iframe communication for AI agents and LLMs

Canonical AI conversation schema — a portable message format for agent threads

Learned skill delivery for LangGraph agents through CopilotKit Intelligence

A robust three-tier LLM-aware caching SDK using Redis, ChromaDB, and automatic SQLite bootstrap.

A fast, lightweight harness for building production AI agents: agents, sub-agents, skills, prompts, tools, MCP, memory and the runtime rails underneath them.

Production-ready framework for building AI agents — type-safe, observable, circuit-broken.

A seatbelt for AI agents: budget caps, rate limits, time limits, loop detection and endpoint filters for any Python agent.

Agentic Security Framework & Real-Time Threat Visualization Engine

An agent framework that keeps configuration (Agent) and history (State) apart, with a plain Python function as the loop

Anthropic infrastructure FinOps SDK — part of the Hyperscaler Radar suite.

Anthropic provider for BindAI

Blast-fragmentation prediction from a bench pattern: the published ladder from Kuz-Ram to stacking ensembles, scored on real measured blasts under three split protocols, with the statistic named (variance explained, not squared correlation).

A drop-in semantic cache for LLM APIs: match requests by meaning, serve repeats instantly, and route across OpenAI, Gemini, Groq, Claude, Ollama and Bedrock.

The production toolkit for LLM calls: caching, retries, fallback, cost tracking, security and structured output in one decorator.

ChromeRAG: ingest-time elimination of site template noise for enterprise web RAG.

ChronoLLM CLI — Chat with temporally consistent language models

CrewAI tools that let agents discover APIs, MCP servers and CLIs through the Agent Nexus registry

Gate a LangChain agent's tool calls with a CTRLRun policy, through wrap_tool_call.

Local phishing-detection agent for the Cybersecurity Browser Extension (Chrome)

Multi-tenant, fail-closed Sphinx RAG extension for the doxtr ecosystem (dual-store ChromaDB knowledge base with security-classified xlinks).

Governance + orchestration framework wrapping the Anthropic Claude API for enterprise deployments

e-volv Observer for Agents SDK for Python: agent runs, model calls and tool calls as spans the Observer rollup reads, with OpenAI, Anthropic and MCP wrappers.

Python client for FeedMyAgent — the technology intelligence feed for AI agents

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

A hunch engine plugin: local models served by Ollama, read through their token probabilities

Provider-neutral asynchronous agent runtime

Claude Agent SDK recording and replay adapter for Kitaru.

LangChain tools and toolkit for FeedMyAgent — the technology intelligence feed for AI agents

Runtime sandbox integration for Deep Agents

GridGain checkpointer, store and node cache for LangGraph — short-term thread state, long-term cross-thread memory, and node-level caching.

The LangGraph side of agent-wait: ask() to declare a question at the interrupt site, an adapter that reads what a thread is parked on, and helpers for the host's start/resume routing.

Declarative synchronization CLI for LiteLLM models, credentials, access groups and virtual keys.

LlamaIndex tool spec that lets agents discover APIs, MCP servers and CLIs through the Agent Nexus registry