Skip to content
DidWork logo

DidWork

Verifies agent work outcomes by checking independent evidence before marking tasks complete.

At a glanceswept 2026-10-09

≈ 1visits/mo

Emerging · estimate, read 2026-09-25

For
Teams building AI agents that need to verify agent actions actually succeeded before continuing.
Price
Free plan · From $49/mopricing page, read 2026-09-25 ↗
Activity
Actively maintainedsite updated 5 days ago
Company
founding year not on record
Runs as
API
What people do with itread off didwork.sh on 2026-09-25
  • Verify agent-reported outcomes against external systems like Stripe
  • Catch incomplete or incorrect agent work before proceeding to next steps
  • Monitor ongoing conditions with watches that check every 5-60 minutes
How a program reaches itfound, not claimed · read 2026-10-13
  • MCP serversh.didwork/didworkverified in the MCP registry
  • Statenot asked yet
  • MCP docsdidwork.sh/mcpthe vendor's page ↗

MCP server details →

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.

Alternatives in Securityby use, among tools still maintained

Figure and bar: visits/mo, estimate · year: online since

All Security tools →

Questions this page answers
  • What is DidWork?

    Verifies agent work outcomes by checking independent evidence before marking tasks complete. It is listed in the Atlas under Security.

  • Who is DidWork for?

    Teams building AI agents that need to verify agent actions actually succeeded before continuing.

  • How much does DidWork cost?

    DidWork has a free plan; paid plans start at $49/mo, per its pricing page on 2026-09-25.

  • Is DidWork free?

    Yes, DidWork has a free plan, per its pricing page on 2026-09-25.

  • Do people use DidWork?

    Emerging: ≈ 1 visits/mo · estimate, 2026-09.

  • Is DidWork still maintained?

    Actively maintained: site updated 5 days ago.

  • What are alternatives to DidWork?

    In Security, by use: OpenBox, Difinity.ai, Agent Checker, THREAT‑WATCH, BoringSec, Panguard.AI.

Not quite it? Describe the job

beta

Five tools from the Atlas that fit it, each judged against what you wrote.

How we read a tool

No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.

  • Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
  • Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
  • Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
  • The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.

How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.