Launch
ThinHarness
Visit
Example Image

ThinHarness

Build focused AI agents without framework sprawl

Visit

ThinHarness is a minimal, opinionated Python harness for purpose-built agents.

It owns the focused set of primitives that are tedious to rebuild and leaves the rest of the stack to your app.

It matches the harness-level feature coverage of frameworks 5–10× its size, so forking is a real option, not a theoretical one.

Pre-1.0, MIT licensed, Python 3.11+.

Example Image
Example Image

Features

  • Scoped filesystem tools
  • Structured output
  • Tool retries
  • Human approvals
  • Subagents
  • Parallel LLM calls
  • Skills
  • MCP
  • Limits
  • Event streaming
  • OpenTelemetry tracing

Use Cases

  • Information retrieval
  • Customer support
  • Workflow automation
  • Many more

Comments

I started building ThinHarness after getting tired with huge agent frameworks. I usually needed only a small slice of functionality, but that slice came with coupled assumptions that didn't match my application. I've been using it for all my agent projects recently but would love feedback from anyone building agent workflows in Python!

Premium Products

Comments

I started building ThinHarness after getting tired with huge agent frameworks. I usually needed only a small slice of functionality, but that slice came with coupled assumptions that didn't match my application. I've been using it for all my agent projects recently but would love feedback from anyone building agent workflows in Python!

Premium Products