# AI Agent Tools With a Free Tier

> Source: https://theagentsindex.com/collections/ai-agent-tools-with-a-free-tier (curated, quality-gated, re-verified)

We checked every listing in our index against its own transcribed, dated pricing tiers and found 55 of 145 offer a genuine, ongoing way to use the product at zero cost: not a time-limited trial, not a one-off credit grant, but a tier you can stay on indefinitely. The most common route to $0 here is not a free plan at all: more of these tools are open-source than not, and for those the free tier is the licence. You self-host and pay only your own model provider. The split is not even across categories: coding agents (21 of 28), agent frameworks (15 of 16) and agent platforms (14 of 33) overwhelmingly let you start free, because these are self-serve, developer-led purchases where the vendor wants a working integration in your hands before you ever talk to sales. Junie shows how thin a qualifying tier can be: its AI Free plan carries no expiry, and it stays free-tier-eligible even though its 3 AI Credits per 30 days leave little headroom for actual agentic runs. It is the same "real but thin" free tier this collection already accepts elsewhere. Support agents are the mirror image: not one of the site's 14 support-agent listings has an ongoing free plan, and every one is sold through a pilot, a per-resolution contract, or a time-limited trial that converts to paid. Voice agents stay sparse (3 of 23): most platforms price per minute from the first call, with only trial credits standing in for a free tier. Cartesia, the newest of them, is the clearest exception: a $0/month tier carrying 20,000 model credits and a small prepaid agent balance, which its own pricing copy distinguishes from a trial.

We deliberately excluded 5 tools whose pricing page uses free-sounding language that doesn't hold up to that bar. Vapi and Retell AI each disclose, in their own pricing copy, trial-credit-only language (Vapi: 'no permanent free tier'; Retell AI: '$10 in free credits, no commitment'). Both are usage-priced per minute from the first call once credits run out. Bland AI waives a separate platform fee on its entry tier but still bills per minute from call one. Intercom Fin and PolyAI each offer a real trial, 14 days and 2 months respectively, that converts to a paid, sales-led plan, not an ongoing free option. None of the 5 are wrong to consider, since a free trial is still a real way to test a tool, but they answer a different buyer question than 'can I keep using this for free,' so we left them off this list rather than blur the two.

| Name | What it is | Why it's here | Pricing | API |
| --- | --- | --- | --- | --- |
| [Cursor](https://theagentsindex.com/cursor.md) | Coding agent in a desktop editor, terminal CLI, cloud VMs and CI, priced per seat plus token usage. | The Hobby tier is free forever with limited agent usage: enough to try Cursor before choosing a paid plan. | — | Yes |
| [GitHub Copilot](https://theagentsindex.com/github-copilot.md) | GitHub's AI coding assistant and cloud agent, from editor completions to pull-request review. | 2,000 code completions and 50 chat requests per month, forever: the most generous free coding-agent tier we found. | — | Yes |
| [Devin Desktop](https://theagentsindex.com/windsurf.md) | AI IDE with a Kanban command center for running local and cloud coding agents; the renamed Windsurf. | The full IDE is free with limited agent usage: a real, ongoing plan, not a time-boxed trial. | — | Yes |
| [Cline](https://theagentsindex.com/cline.md) | Open-source coding agent for VS Code, JetBrains, the terminal and CI, running on whichever model you bring. | Free forever and open-source (Apache-2.0): you only ever pay your own model provider for API usage. | — | Yes |
| [Aider](https://theagentsindex.com/aider.md) | Open-source terminal AI pair programmer that edits files in your local git repo and commits the changes. | Free forever and open-source (Apache-2.0): bring your own API key, or run a local model for zero cost. | — | Yes |
| [Replit Agent](https://theagentsindex.com/replit-agent.md) | Chat-driven agent that builds, tests and publishes full web and mobile apps on Replit's cloud. | The Starter tier grants free daily Agent credits and lets you publish one project, ongoing. | — | Yes |
| [Bolt](https://theagentsindex.com/bolt-new.md) | Browser-based AI agent that builds, hosts and publishes full-stack JavaScript web and mobile apps from prompts. | 300K daily / 1M monthly tokens free, forever: Bolt branding included on generated sites at this tier. | — | No |
| [Juggler](https://theagentsindex.com/juggler.md) | Visual workbench for AI coding agents: branching conversation trees, inspectable model transactions, local or remote. | Free forever, open-source (AGPLv3 + Apache-2.0 SDK): no signup or account, bring your own model key. | — | No |
| [Codex CLI](https://theagentsindex.com/codex-cli.md) | OpenAI's terminal coding agent for inspecting, editing and running repository code from the shell. | The ChatGPT Free plan includes limited Codex access and limited GPT-5.5 Instant access. | — | Yes |
| [OpenCode](https://theagentsindex.com/opencode.md) | Open source AI coding agent for the terminal, desktop app and IDE, with 75+ model providers. | Free, unlimited local use with your own API key across 75+ providers, or run local Ollama models at zero cost. | — | Yes |
| [zot](https://theagentsindex.com/zot.md) | Single-binary terminal coding agent harness in Go, with 30+ model providers and any-language extensions. | Free forever, open-source (MIT): a single Go binary with no signup, bring your own key or run local Ollama models. | — | Yes |
| [OpenHands](https://theagentsindex.com/openhands.md) | Open-source software engineering agent with GUI, CLI, SDK and an enterprise control plane. | The open-source core is free (MIT, self-hosted); a free hosted Cloud tier is also available, capped at 1 user and 10 conversations/day. | — | Yes |
| [CodeRabbit](https://theagentsindex.com/coderabbit.md) | AI code review across pull requests, IDE and CLI, with agentic fixes, pre-merge checks and security review. | Unlimited public and private repos free, forever, plus a 14-day trial of the paid Pro Plus tier layered on top. | — | Yes |
| [Antigravity CLI](https://theagentsindex.com/antigravity-cli.md) | Google's terminal agent: a keyboard-driven TUI that edits code, spawns subagents and gates every tool call. | The Individual tier is free with unlimited tab completions and command requests, on a weekly-refreshing rate limit. | — | Yes |
| [Warp](https://theagentsindex.com/warp.md) | Agentic development environment: a terminal, a standalone agent CLI, and unattended cloud coding agents. | 150 credits/month free for the first two months, then 75/month ongoing: reduced, but never zero. | — | Yes |
| [LangChain](https://theagentsindex.com/langchain.md) | Open source agent frameworks plus LangSmith, a hosted platform to trace, evaluate, deploy and govern agents. | The core framework is free open-source; LangSmith's Developer tier adds free observability up to 5,000 traces/month. | — | Yes |
| [CrewAI](https://theagentsindex.com/crewai.md) | Open-source multi-agent framework with a managed platform for deploying and governing agent workflows. | The framework is free open-source; the hosted AMP Basic tier adds 50 free workflow executions/month. | — | Yes |
| [AutoGen](https://theagentsindex.com/microsoft-autogen.md) | Open-source Microsoft framework for building single and multi-agent AI applications in Python. | Microsoft's framework is free, open-source (MIT) and self-hosted: pay only your own model provider. | — | Yes |
| [LlamaIndex](https://theagentsindex.com/llamaindex.md) | Open-source agent framework plus a credit-metered document parsing, extraction and indexing platform. | The core framework is free open-source; LlamaCloud Free adds 10,000 parsing credits/month for managed extraction. | — | Yes |
| [OpenAI Agents SDK (Python)](https://theagentsindex.com/openai-agents-sdk.md) | Open-source Python framework for building agents with tools, handoffs, guardrails and tracing. | Free and open-source (MIT), self-hosted: pay only for the model API you call. | — | Yes |
| [Pydantic AI](https://theagentsindex.com/pydantic-ai.md) | Open-source Python agent framework from the Pydantic team, with a typed agent loop and swappable models. | Free and open-source, self-hosted: pay only your own model provider; the optional Logfire observability layer has its own free tier too. | — | Yes |
| [Mastra](https://theagentsindex.com/mastra.md) | Open-source TypeScript framework for building AI agents, with a hosted platform for running and observing them. | Self-hosted (Apache-2.0) is free forever; the Starter Cloud tier adds 100K free observability events/month. | — | Yes |
| [Letta](https://theagentsindex.com/letta.md) | Stateful agent harness, cloud and SDK for agents with persistent, git-versioned memory. | The Free tier runs a limited number of agents with your own API keys, ongoing. | — | Yes |
| [n8n](https://theagentsindex.com/n8n.md) | Workflow automation platform for building and running AI agents on a visual canvas, with code where needed. | The self-hosted Community edition is free forever under n8n's fair-code license. | — | Yes |
| [Relevance AI](https://theagentsindex.com/relevance-ai.md) | Platform for building and running specialist business agents and multi-agent workforces. | ~200 free Actions/month with starter Vendor Credits: no card required to start building. | — | Yes |
| [Dify](https://theagentsindex.com/dify.md) | Open-source platform for building agentic workflows, AI agents and RAG knowledge pipelines. | The self-hosted Community Edition is free forever (all core features); a Sandbox cloud tier adds 200 free message credits/month. | — | Yes |
| [Salesforce Agentforce](https://theagentsindex.com/salesforce-agentforce.md) | Salesforce's platform for building, deploying and monitoring AI agents on top of CRM data. | The Foundations tier includes 200,000 free Flex Credits plus 250,000 Data Cloud credits, ongoing. | — | Yes |
| [Perplexity](https://theagentsindex.com/perplexity.md) | AI answer engine with an agentic Computer, the Comet browser, and a developer API for web-grounded search. | The Free plan includes limited Pro Search and a few Deep Research runs per day. | — | Yes |
| [Manus](https://theagentsindex.com/manus.md) | General-purpose AI agent that plans and executes multi-step tasks on its own cloud computer. | ~300 daily refresh credits free, no card required: roughly one task a day at zero cost. | — | Yes |
| [GPT Researcher](https://theagentsindex.com/gpt-researcher.md) | Open-source autonomous research agent that writes cited long-form reports from web and local sources. | Free and open-source (Apache-2.0), self-hosted with unlimited use: you pay only your own LLM/search API costs. | — | Yes |
| [Elicit](https://theagentsindex.com/elicit.md) | Research agent that searches 138M+ papers and runs systematic reviews with sentence-level citations. | The Basic tier searches 138M+ papers and summarizes them unlimited, free, with limited Research Agent usage. | — | Yes |
| [Undermind](https://theagentsindex.com/undermind.md) | AI co-researcher that runs deep literature searches over 200M+ scientific papers and cites every source. | The Free tier includes AI chat, deep searches and reports with standard rate limits, ongoing, not a time-limited trial. | — | Yes |
| [Rox](https://theagentsindex.com/rox.md) | Revenue agents that research accounts, prospect, run outbound and manage deals, metered in Agent Actions. | The Starter tier includes 2,000 free agent actions/month, ongoing, for individuals running light pipeline generation. | — | Yes |
| [Unify](https://theagentsindex.com/unify.md) | AI outbound agents that prospect, research and sequence from one chat interface. | The Free tier supports up to 3 seats with limited credits across its full contact/company database. | — | Yes |
| [ElevenLabs Agents](https://theagentsindex.com/elevenlabs-conversational-ai.md) | Hosted platform for building voice and chat agents, with telephony, SDKs and a choice of LLM. | 15 free call minutes/month across 4 concurrent calls, ongoing: LLM and telephony usage billed separately. | — | Yes |
| [LiveKit Agents](https://theagentsindex.com/livekit-agents.md) | Open-source Python and Node.js framework for voice AI agents, with LiveKit Cloud hosting, telephony and observability. | 1,000 free agent-session minutes/month, 5 concurrent sessions, no card required. | — | Yes |
| [Zed](https://theagentsindex.com/zed.md) | Rust-based code editor with a built-in agent panel, ACP external agents and Zed-hosted models. | The Personal tier is free forever: 2,000 accepted edit predictions/month plus unlimited use of AI features with your own API keys or external agents. | — | Yes |
| [Microsoft Agent Framework](https://theagentsindex.com/microsoft-agent-framework.md) | Open-source .NET, Python and Go SDK for building AI agents and graph-based multi-agent workflows. | Free and open-source (self-hosted) across .NET, Python and Go: pay only your own model provider; the managed Foundry Hosted Agents layer is a separate, metered add-on. | — | Yes |
| [Google Agent Development Kit (ADK)](https://theagentsindex.com/google-adk.md) | Open-source framework for building, evaluating and deploying AI agents in Python, TypeScript, Go, Java or Kotlin. | Free and open-source (self-hosted, Apache-2.0) across all four language SDKs: pay only your own model provider; the managed Agent Runtime on Google Cloud layers on a metered add-on, not a requirement. | — | Yes |
| [Claude Agent SDK](https://theagentsindex.com/claude-agent-sdk.md) | Python and TypeScript library that runs Claude Code's agent loop and tools inside your own application. | The SDK itself is free: self-hosted, pay only standard Claude API token rates for what the agent actually uses; the separate Claude Managed Agents hosted layer adds a metered $0.08/session-hour on top, not a requirement. | — | Yes |
| [Cartesia](https://theagentsindex.com/cartesia.md) | Real-time speech models and a managed runtime for production phone and web voice agents. | A genuine $0/month tier (20,000 model credits plus a small prepaid agent balance) that you can stay on indefinitely, rather than the trial credits most of this category offers, with flat $0.06/min agent pricing that does not change on the paid tiers above it. | — | Yes |
| [Junie](https://theagentsindex.com/junie.md) | JetBrains coding agent for the terminal, JetBrains IDEs and CI, running on hosted or your own model keys. | The AI Free plan is $0/month with no stated expiry (3 AI Credits per 30 days plus unlimited use of locally-run models): real but thin, the same shape this collection already accepts elsewhere. | — | Yes |
| [Augment Code](https://theagentsindex.com/augment-code.md) | Cosmos platform running fleets of coding agents across the SDLC, plus Auggie CLI and IDE extensions. | The Community tier is listed at $0/month with no stated expiry, alongside the paid Business and Enterprise tiers: an ongoing plan, not a time-boxed trial. | — | Yes |
| [Agno](https://theagentsindex.com/agno.md) | Python SDK, self-hosted AgentOS runtime and hosted control plane for building and operating agent platforms. | The Free tier carries the full open-source Agent Framework plus a local AgentOS control plane for chat, session monitoring and evaluations, with no stated expiry. | — | Yes |
| [Botpress](https://theagentsindex.com/botpress.md) | AI agent platform with a visual studio, a code-first TypeScript ADK and a helpdesk, priced per conversation. | Two ongoing free paths: a Pay-as-you-go tier with ~500 incoming messages/month and $5/month of AI credit included, plus an MIT-licensed core you can self-host outright. | — | Yes |
| [Browserbase](https://theagentsindex.com/browserbase.md) | Cloud headless browsers, search/fetch APIs and managed browser agents behind one API key. | The Free tier is listed at $0/month alongside the paid Developer, Startup and Scale plans: an ongoing plan, not a time-boxed trial. | — | Yes |
| [Genspark](https://theagentsindex.com/genspark.md) | All-in-one AI workspace with autonomous agents for slides, docs, sheets, code, media and scheduled automation. | The Free tier refreshes ~100 credits daily with about 1GB of storage and basic Super Agent access, no credit card required. | — | Yes |
| [Julius AI](https://theagentsindex.com/julius-ai.md) | AI workspace that researches, runs Python/R and SQL analysis, and builds decks, reports, sites and video. | The Free tier is listed at $0/month beneath four paid plans: an ongoing tier rather than a trial that converts. | — | No |
| [LangGraph](https://theagentsindex.com/langgraph.md) | Open-source orchestration framework and runtime for stateful, long-running LLM agents, from LangChain. | The framework ships as a free, MIT-licensed Python and JavaScript library; the hosted Developer plan sits at $0/seat/month on top of it. | — | Yes |
| [OpenClaw](https://theagentsindex.com/openclaw.md) | Open-source personal agent runtime you host yourself and message from any chat app. | Free forever and open-source (MIT), self-hosted: the managed Elestio option bills only for disk and compute, and its tier-1 support is included at no cost. | — | Yes |
| [AgentsKit](https://theagentsindex.com/agentskit.md) | Composable TypeScript packages for agent runtime, tools, memory, RAG and headless chat UI. | Free and open-source (MIT), self-hosted across all 22 @agentskit packages: the free path is the licence rather than a priced plan, so you pay only your own model provider. | — | Yes |
| [goose](https://theagentsindex.com/goose.md) | Open-source local AI agent — desktop app, CLI and ACP server — running on the LLM provider you bring. | Free and open-source (Apache 2.0) under the Linux Foundation: the desktop/CLI coding agent ships with 70+ MCP extensions across 15+ LLM providers and no signup. | — | Yes |
| [MindStudio](https://theagentsindex.com/mindstudio.md) | No-code platform for building, running and deploying AI agents as drag-and-drop workflows. | A free tier with 1 agent and 1,000 runs/month, ongoing: sits beneath the paid Individual ($20/month) and Business tiers for the no-code visual builder. | — | Yes |
| [Kilo Code](https://theagentsindex.com/kilo-code.md) | Open source AI coding agent for VS Code, JetBrains, CLI and cloud, with 500+ models at provider rates. | The Individual platform tier is free, alongside Teams ($15/mo) and Enterprise; AI inference bills separately via BYOK or Kilo Pass credits from $19/mo. | — | Yes |
| [Vellum](https://theagentsindex.com/vellum-ai.md) | Open-source personal AI assistant with long-term memory that acts across your tools, in the cloud or self-hosted. | A free Base plan with paid packages starting at $30/mo: an ongoing $0 tier rather than a trial that converts for the personal assistant with persistent memory and built-in skills. | — | Yes |

## How this list is built

A tool earns a place here only if its own Published, sourced pricing evidence shows an ongoing, indefinite way to use it at $0: self-hosted and free forever, a permanent free-forever plan, or a cloud tier with a real recurring usage allowance and no stated expiry. A time-limited trial (however generous), a one-time credit grant, or a platform-fee waiver that still bills usage from the first action does not qualify, even where a vendor's own marketing calls it "free." Verified against each listing's dated pricingTiers array, not a vendor's marketing headline. Where a tool's free path is an open-source licence rather than a priced plan, we verify instead against its own published licence and self-host deployment fields. 5 candidates were checked and excluded for this exact reason (see intro); Vapi, Retell AI and Bland AI are each now marked as having no free tier on their own listing, matching their own already-published pricing copy.