Business agents

Provider-agnostic action defender SDK for AI agents

Real-time memory health monitor and context rot detector for AI agents

Local agentic benchmark suite for MLX and OpenAI-compatible inference engines.

The Reliability Layer for Autonomous AI Agents — full tracing, cost intelligence, guardrails, and quality evaluation.

Forge — an open-source, enterprise-ready multi-agent orchestration platform with cost awareness, governance, and security built in.

Provider implementations and common tools for AgentHarness (Anthropic, OpenAI, Ollama) behind optional extras.

Build inspectable AI agents with ordinary Python functions and no workflow DSL.

Agent Operating System — Production-ready multi-model agent framework with Tool-Using Agent, LLM Provider abstraction (OpenAI/DeepSeek/Anthropic), Function Calling, streaming, retry, checkpoint/resume, A2A protocol, swarm coordination, and comprehensive observability.

Retrieval-only MCP server over the indexed React documentation, with a prebuilt index downloaded on first run.

Windows tray widget + dashboard for Claude plan usage (5-hour & weekly limits)

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.

Route a Hermes Agent's local Ollama traffic through the native /api/chat API (honors num_ctx + correct tool-call streaming) instead of the OpenAI-compat /v1 endpoint.

Cached LLM client with Ollama + Anthropic provider dispatch, fixture mode, and JSON-schema-strict completions.

SurrealDB checkpoint persistence and cross-thread stores for LangGraph.

A global reusable LLM Registry wrapper for LangChain models with unified error mapping for Lighthouse Agents Factory

llama-index tools chronoverify integration

LiteLLM CustomLLM plugin for llm-catalog: drive a catalog config through LiteLLM, in-process or via the proxy.

Pydantic AI adapter for llm-catalog: build native Pydantic AI models from a catalog config, routed through your gateway.

Bidirectional UUID<->numeric ID mapping to shrink LLM prompt token counts for large item lists.

LLM API latency benchmarker: TTFT p50/p95/p99 (cold/warm cache split), tokens/sec, cost.

Run any LLM with one config file. No framework lock-in.

Moxie — the open-source money agent that acts on your money, only with your approval. Local-first, consent-first.

Circuit breaker SDK for LLM agents.

pytest for RAG agents — behavioral audits with PASS/FAIL/WEAK verdicts

Salesforce OAuth 2.0 / OAuth 2.1 / OIDC 1.0 identity provider implementations for Swarmauri

A smart, OpenAI-compatible LLM router — a tiny triage-verify-escalate agent that saves cost without losing quality.

Model providers for lite-agent: Anthropic Messages API + OpenAI Chat Completions (also OpenAI-compatible / local endpoints).

Unified LLM API with automatic model discovery and provider configuration

LLM facade Django app for the Stapel framework

Referent review: compare features, pricing, use cases, access model, and alternatives for this Legal agent in 2026. Legal AI for Lawyers and Law Firms: CRM, Matters, and Practice Management

Backend for @hamak/ai-agent: hosted-model providers (Anthropic), durable memory, and an Express agent-chat route

Local copy-paste runtime for the AIFluensLab learning labs. Build and run an agent on your own machine with your own provider key.

OpenTelemetry-based observability SDK for AI applications

Pi package for Pinet Slack assistant integration — multi-agent broker, thread routing, and inbox tools

Multi-Agent AI Collaboration Platform with Tmux Orchestration

Three-tier LangGraph checkpoint saver: L1 SQLite -> L2 NATS KV -> L3 PostgreSQL

Autonomous MCP agent for graduate school applications: prof discovery + verified cold emails + SOP drafting + application tracking.

CLI for OpenAI and Anthropic organization cost reports

Production-grade RAG for Python: ingest documents, hybrid search, streaming, multi-LLM, guardrails. CLI + Python API.

Claude Target adapter for Waken — routes waken Events to the Claude Agent SDK.

CLI for creating and managing Rootstock Salesforce DX projects with AI agent scaffolding

LangChain.js security integration for Weave Protocol - callbacks, tool wrappers, and retriever guards

Drop-in React chatbot and AI agent widget — streaming chat UI for OpenAI, Anthropic, AWS Bedrock, Azure OpenAI, or any custom API. Fully themeable, TypeScript-first, zero CSS-in-JS.

An **[MCP](https://modelcontextprotocol.io) server** for asynchronous execution, bounded status observation, and in-place stopping of dynamic multi-agent workflows. Execution lives in a shared per-user **local daemon** (spec-compliant Streamable HTTP on l

Agentic Finance (AIFI): turn Agent402's catalog - 500+ strong: 400+ pay-per-call tools (x402 or MPP) + 100+ skill packs - into LangChain and CrewAI tools for Python agents. Free tier via proof-of-work - no wallet, no API keys.

Andreas Christodoulou review: compare features, pricing, use cases, access model, and alternatives for this Marketing agent in 2026. Rated 5/5 from 1 verified review. 👔 Entrepreneur - 🤝🏻 Business | Tech | Digital Marketing

Speaker reveals, agenda drops, ticket waves, and sponsorship openings — announced to subscribers first.

SUDO-AI - Autonomous AI Agent Platform

Hyacinth 🪻 — multi-provider AI agent with tool system and context management

n8n AI Agent node with native Langfuse integration: tracing + prompt management

Pylva SDK — cost infrastructure for AI agent businesses

Universal multi-framework AI agent sets system — 41 specialized subagents across 18 agent sets

Build an LLM agent with spending limits, a tamper-evident audit trail, PII redaction, and record/replay testing built in from the start — a governed agent in about 10 lines.

Model Context Protocol server for backtest-kit: lets an LLM agent observe the live trading portfolio and open or close positions through guarded tools

Static analysis CLI that finds deterministic LLM-agent cost-exposure bugs (unbounded retry loops, unbounded while(true) agents, leaked system prompts) and computes a worst-case dollar exposure ceiling from real, dated model pricing.

Provider-neutral model adapter layer: canonical messages, capabilities, streaming contract

Mastra-backed AgentHarness implementation for @salesforce/sfdx-agent-sdk

Rulvar first-class provider adapter over @anthropic-ai/sdk.

A TypeScript framework for building AI agent-powered applications. Integrates with multiple LLM providers (OpenAI, Anthropic, Ollama, Fireworks) and implements the AG-UI protocol for real-time frontend communication.

Claude Agent SDK-backed AgentHarness implementation for @salesforce/sfdx-agent-sdk

A drop-in spend cap and audit log for LLM API calls

Gateway Agnostic SDK for Punk's hosted AI gateway: OpenAI, Anthropic, OpenRouter, Vercel AI SDK, LangChain, agent tracing, tool caching, and governance.

LangSmith tracing for skein-js — run identity and thread grouping on every graph call.

Route LangGraph.js tool calls through toolgovern's governTool() gate before they reach ToolNode -- wraps each tool with the classifier, then re-wraps it with LangChain's own tool() factory so it slots into new ToolNode([...]) unchanged.

Robyn framework adapters — gasless cross-chain tools for Vercel AI SDK, LangChain, Coinbase AgentKit, and raw OpenAI/Anthropic function-calling.

Standalone documentation agent for Ollama and OpenAI-compatible providers

Mastyf AI security middleware for LangChain — intercepts and evaluates tool calls through the Mastyf policy proxy

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

AI agent packaging for HTTP QUERY — OpenAPI tool schemas, MCP, Vercel AI SDK, LangChain helpers.

TypeScript Fastify AI protocol gateway for OpenAI, Anthropic, Gemini, MCP and agent workflows.

Eden TypeScript runtime SDK — auto-instrumentation for OpenAI, Anthropic, Vercel AI, LangChain, Mastra, Bedrock, and Gemini with fire-and-forget telemetry to the Eden gateway.

Rulvar umbrella package: re-exports @rulvar/core, both first-class adapters, the file store, and the terminal progress renderer. Also installable through the unscoped alias package rulvar, which re-exports this one.

Aegis - local-first, policy-gated CLI agent. All effects go through a Policy Gateway; changes happen in an isolated worktree; every action is auditable.

In-process subagents for Pi with isolated SDK sessions, parallel and chained delegation, and inspectable threads.

lyra CLI: a Sui-native, policy-bound AI finance agent. Real on-chain work gated by deterministic policy, simulation, and approval

WebAssembly/JS bindings for the llmtrim-core compression engine (wasm-bindgen).

Versatile autonomous AI agent with three-agent architecture (Manager, Worker, Client) powered by gpt-oss-120b. Adaptive validation, full MCP support, and intelligent quality control.

Unified LLM provider SDK for HoloScript - OpenAI, Anthropic, Gemini, OpenRouter, xAI, and local LLM adapters

Declarative orchestration + observability for autonomous agent loops on the Claude Agent SDK

iTechSmart UAIO MCP Server - connect any AI agent to ProofLink verification and autonomous IT operations

Core library for herdctl fleet management

Shared chat infrastructure for herdctl connectors

MCP server for action governance on AI agents — 14 tools that govern tool calls, SQL queries, file writes, shell commands, and agent-to-agent messages server-side, before execution. Allow / approve / block. Session correlation. Works with Claude Desktop,

Matter all-in-one Home Assistant Add-on with complete Scrypted, BLE, Smart Dimmers, Vacuum, AC, Climate, Lock and Multi-Platform ecosystem compatibility

Multi-agent swarm intelligence with neural mapping, digital twin persona adaptation, crawl4ai, MCP, and bias-reduced consensus. 20+ AI providers.

Lightweight, embeddable pump.fun sniper engine for 3D AI agents — multi-agent, multi-user, with pluggable wallet/store/RPC adapters. Library + CLI + MCP server + x402 paid API.

Anthropic Messages API chat client for the Agent Framework, built on the official @anthropic-ai/sdk.

Opinionated WhatsApp Cloud API agent framework for Cloudflare Workers — Drizzle-backed stores, D1-coalesced webhook queue, AI assistant integration with pluggable reply enrichment, opt-in CRM, account-link redemption, broadcast cron, sequential drip plans

A powerful AI Agent framework for Node.js - all-in-one package

MCP server for agentic passwordless SSH/SCP with ControlMaster connection reuse

MCP server for agentic Docker container operations via docker exec and docker cp

Capital Agentic Charts is the standalone Bun/TypeScript runtime for Capital Companion's agentic financial chart workspace. The chart is a durable trade reasoning document, not transient Canvas or React state. Users and agents mutate charts through typed `

Capital Agentic Charts is the standalone Bun/TypeScript runtime for Capital Companion's agentic financial chart workspace. The chart is a durable trade reasoning document, not transient Canvas or React state. Users and agents mutate charts through typed `

Capital Agentic Charts is the standalone Bun/TypeScript runtime for Capital Companion's agentic financial chart workspace. The chart is a durable trade reasoning document, not transient Canvas or React state. Users and agents mutate charts through typed `

Capital Agentic Charts is the standalone Bun/TypeScript runtime for Capital Companion's agentic financial chart workspace. The chart is a durable trade reasoning document, not transient Canvas or React state. Users and agents mutate charts through typed `

Standalone OpenAI-compatible LLM gateway — multi-provider proxy with pluggable inference metering

Capital Agentic Charts is the standalone Bun/TypeScript runtime for Capital Companion's agentic financial chart workspace. The chart is a durable trade reasoning document, not transient Canvas or React state. Users and agents mutate charts through typed `

Agentic TAM mapping from natural language.

helmwart scan — design-time threat modeling for agentic-AI systems, in your CI. Reads a real agent config (MCP, n8n, LangGraph, CrewAI, and more) and reports its threat model against OWASP Agentic Top 10, MAESTRO, and MITRE ATLAS — including the lethal-tr