Best Free AI Agent tools

A platform for building and running durable AI agents with managed sessions, event logging, and automatic crash recovery.

Run any LLM locally on your Mac faster than LM Studio or Ollama, with chat, coding agents, images, video, and voice, all fully offline and open source.

Mirrors turns your production traces into an isolated copy of your agent's environment so you can test changes safely.

An open-source CLI for fast local search across your past coding agent sessions.

Valmis is an open-source AI agent platform for automating business workflows securely, with isolated containers, proxy API access, and multi-step automation.

Sequence is the financial execution layer for AI agents, enabling them to send, split, and route real money across bank accounts, cards, apps, and loans via a single API.

N71 gives all your AI agents one shared context by maintaining a living knowledge graph connected to your tools, so every agent stays current without re-explaining.

Extract web data and automate browsers via a single API call, no scraper required.

Behavioral infrastructure for humanlike AI agents, providing APIs and models for social intelligence in group interactions.

Acti is an agentic keyboard for mobile that understands your intent and delivers results, links, or actions without leaving the conversation.

A platform for building and running durable AI agents with managed sessions, event logging, and automatic crash recovery.

Run any LLM locally on your Mac faster than LM Studio or Ollama, with chat, coding agents, images, video, and voice, all fully offline and open source.

Mirrors turns your production traces into an isolated copy of your agent's environment so you can test changes safely.

An open-source CLI for fast local search across your past coding agent sessions.

Valmis is an open-source AI agent platform for automating business workflows securely, with isolated containers, proxy API access, and multi-step automation.

AI-native email deliverability service combining AI agents and human experts to monitor, audit, and improve inbox placement with daily monitoring and weekly reporting.

Sequence is the financial execution layer for AI agents, enabling them to send, split, and route real money across bank accounts, cards, apps, and loans via a single API.

N71 gives all your AI agents one shared context by maintaining a living knowledge graph connected to your tools, so every agent stays current without re-explaining.

Extract web data and automate browsers via a single API call, no scraper required.

Behavioral infrastructure for humanlike AI agents, providing APIs and models for social intelligence in group interactions.

Acti is an agentic keyboard for mobile that understands your intent and delivers results, links, or actions without leaving the conversation.

Pluno AI is an AI support agent that learns from past tickets to resolve complex B2B technical issues, integrating with Zendesk.

A unified Python library that combines MCP servers, agent skills, custom functions, and HTTP endpoints into a single tool set for building AI agents with any LLM.

Local-first memory for AI coding agents. Automatically stores and recalls project context via MCP, offline, with ~35ms recall.

A CLI tool that checks package versions for known vulnerabilities across npm, PyPI, and many other ecosystems, designed for AI agents to avoid using outdated packages.

Moxie is an open-source money agent that finds zombie subscriptions, duplicate charges, and missed refunds, then drafts fixes with your consent and logs every step in a tamper-evident audit trail.

Kage is a git-native verification layer for coding agent memory that checks every claim against your code to prevent hallucinations and stale facts.

Clusy is an agent-native notebook that lets you fine-tune LoRA models by simply describing what you want, automating data sourcing, architecture selection, and execution.

AI-powered platform to build custom news trackers that filter noise and deliver insights on any topic.

Folio is an AI agent that generates and edits PowerPoint and Google Slides presentations, tailored for consulting and strategy teams.

Real-time event monitoring infrastructure for AI agents that delivers low-latency data streams and webhook notifications to trigger automated workflows.

Fleet is a local-first web console for creating, configuring, monitoring, and operating Dockerized Hermes AI agents across trusted machines.

Keeps your Mac awake only while AI coding agents are actively working, and lets it sleep when they finish.

Open-source reliability testing harness for AI agent skills, computing pass@k scores across Claude Code, Codex, and Pi backends.

Open-source alternative to Claude in Slack: self-hosted AI agent that reads threads, answers questions, calls tools, and renders rich results.

Build and deploy production-ready multimodal voice AI agents for sales coaching, interview practice, and leadership training.

Zaro is a workspace to build AI agents, apps, and tools using your company's own data, with shared memory and no vendor lock-in.

Sakana Fugu is a multi-agent system that dynamically orchestrates multiple AI models via a single API to tackle complex multi-step tasks.

A transpiler from stateful imperative workflows to declarative DSPy programs for reliable, optimizable LLM steps with zero boilerplate.

Bluerails provides AI agent payment infrastructure and commerce tools, enabling businesses to be discovered, interacted with, and paid by AI agents.

Assist is an open-model-first work surface for agents that connect to your tools, operate inside your business, and route work across local, open, and frontier models.

Open source authorization engine for AI agents that provides confidence-aware gating, human-in-the-loop review, policy-as-code, and full audit trail.

peerd is the first AI agent harness native to the browser, allowing AI agents to drive tabs, run sandboxed compute, and share peer-to-peer with no backend.

HALO is a methodology and toolkit for recursively self-improving AI agent harnesses using RLMs and production traces.

Alma is a local-first MCP server that gives AI agents a private, consent-based memory of your personal facts and preferences.

Caplets gives AI agents focused capabilities by turning sprawling MCP servers into progressive disclosure cards, reducing context usage and keeping schemas out of prompts until needed.

An AI agent platform for building, evaluating, and deploying multi-agent workflows, with an option to outsource process automation.

OpenHuman is an open-source, personal AI super intelligence that offers a simple, private, and powerful agentic assistant with local memory and managed services.

A self-hostable workspace where humans and AI agents collaborate in shared rooms over a Nostr relay.

Tycoon is a platform that provides an AI CEO and a team of AI employees to help one-person companies build and grow their business automatically.

Velane is an open source AI agent code runtime that connects to your IDE via MCP, enabling autonomous creation, testing, and deployment of workflows with 800+ integrations.

Elvin is a proactive AI assistant that watches your inbox, calendar, and messages, finds what needs doing, and drafts it before you ask.

A multi-agent AI runtime for Python developers with OS-inspired primitives like job scheduling, DAG orchestration, memory, and tool execution.

Claw Patrol is an open-source security firewall for AI agents that guards credentials, gates actions, and logs all traffic.

Memento is an AI tool that surfaces your important history from email, organizing it around people, projects, and topics that matter to you.

ctx is a context-aware recommendation engine that dynamically selects the best skills, agents, and MCPs for your current coding task using a massive knowledge graph.

Local-first AI intelligence engine for macOS that builds private memory from screen OCR, email, and calendar, then provides proactive assistance and autonomous task execution.

Reality Kernel provides causal verification for AI agents by simulating actions across shadow worlds, preventing attacks undetectable by LLM judges.

A Go-native framework for building, orchestrating, and observing AI agents with native OpenTelemetry observability and a self-hosted dashboard.

AIsa provides a single API key for AI agents to access 1000+ LLMs, APIs, and skills with autonomous micropayments.

A platform for building and running durable AI agents with managed sessions, event logging, and automatic crash recovery.

Run any LLM locally on your Mac faster than LM Studio or Ollama, with chat, coding agents, images, video, and voice, all fully offline and open source.

Mirrors turns your production traces into an isolated copy of your agent's environment so you can test changes safely.