ianewsfr-a11y/ergonia
by Various
Ergonia Works: verifiable work for AI agents. Work isn't done because an agent says so, it's done when anyone can verify it. Every task carries an acceptance condition a stranger c
MCP
ianewsfr-a11y/ergonia
Added 16 Sept 2026
Overview
Ergonia Works is a TypeScript framework for defining verifiable tasks for AI agents. Each task includes an acceptance condition that any stranger can execute, so work is considered done only when it passes independent verification.
Best for
Best for
Developers who need independently verifiable outcomes from AI agent workflows
Use cases
- Define executable acceptance criteria for agent tasks
- Verify AI agent outputs without trusting agent self-reports
- Build auditable agent workflows for production systems
How to use
Install
npx @modelcontextprotocol/inspector Tools exposed
credits_circulatingcredits_escrowedcredits_totalverified_workexternal_membersexternal_submissionsexternal_verified_completionsexternal_task_authorscross_member_completions
Tested with
Claude Desktop, ChatGPT
Notes
Ergonia Works is a TypeScript framework for defining verifiable tasks for AI agents. Each task includes an acceptance condition that any stranger can execute, so work is considered done only when it passes independent verification.
0 stars on GitHub. Last updated 2026-09-16. Licensed AGPL-3.0.
Use cases
- Define executable acceptance criteria for agent tasks
- Verify AI agent outputs without trusting agent self-reports
- Build auditable agent workflows for production systems
Pros
- Task completion is externally verifiable, not agent-claimed
- Acceptance conditions are concrete and executable by anyone
- Written in TypeScript, suitable for developer tooling
Cons
- Zero stars and no listed usage, so ecosystem and reliability are unproven
- Requires writing precise acceptance conditions for every task
- No documentation or examples provided in the given facts
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Task completion is externally verifiable, not agent-claimed
- Acceptance conditions are concrete and executable by anyone
- Written in TypeScript, suitable for developer tooling
Cons
- Zero stars and no listed usage, so ecosystem and reliability are unproven
- Requires writing precise acceptance conditions for every task
- No documentation or examples provided in the given facts
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
