OpenAdapt

Open-source layer that turns a recorded task into a replayable program for computer-use agents, with read-back checks on every save

Agent by OpenAdapt.AI

IndexedMIT★ 1,823

Write a review

Chalk Labs

Need help deploying OpenAdapt?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Get started

Setup steps are in the repository. Website · Repository

About

OpenAdapt lets an agent or a person do a task once in a web, Windows, macOS, Linux, RDP or Citrix app, then compiles the recording into a program the agent calls as one tool. The program runs without model calls, checks the record before each save, reads it back afterwards and stops when something does not match. When the app changes, an agent proposes a repair that a person approves. It targets healthcare and portal workflows and runs locally with an MCP server, with a paid Team plan for shared run records and hosted runs.

Use cases: browser-automation, other, workflow-automation

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Jobs: browser automation, otherREADME
Autonomy: Supervised: runs multi-step tasks, asks at checkpointsREADME
Where you use it: Terminal, APIopenadapt.ai
Hosting: Hosted or self-hostedopenadapt.ai
Interfaces: mcp, rest-apiopenadapt.ai
Open source: Yesopenadapt.ai
Billing: Flat monthly price for Team with no per-run charge or overage; a normal run makes no model calls.openadapt.ai

Pricing

Free plan plus paid plans · free tier available

Local	$0	MIT license, unlimited runs on your own machine, community support
Team	$499/month	no per-run charge; hosted runs one at a time
Enterprise	Contact sales	custom; qualification sprints from $15k

As of Oct 24, 2026, from the vendor's pricing page. Prices change; check the vendor before you buy.

Facts extracted by Claude Sonnet 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Signals

Stars: 1,823
Forks: 274
Open issues: 31
Last commit: Oct 24, 2026 (6 days ago)
Last release: Oct 20, 2026 (10 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/OpenAdaptAI/OpenAdapt
Website: openadapt.ai
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README Website Pricing page github-graphql

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped: 50+; launches shipped
media placements: 500+; media placements
founders on every account: 2; founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get OpenAdapt running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Need help deploying OpenAdapt?

Call Get help

Cite this page

OpenAdapt. Agent Mart. https://agentmart.dev/agents/openadapt (last updated 2026-10-24)