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

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!

ThinHarness is a lightweight, minimal agent framework with clean code, built-in parallel LLM calls and powerful search tools, free of bloated extra layers for flexible custom business agent development.

custom-img
i write a16z speedrun scout checks withi...

This is exactly what the agent ecosystem needed. So many frameworks push you into their opinionated stack, but most projects just need focused primitives - filesystem tools, structured output, retries. The fact that ThinHarness gets you 5-10x framework coverage in a tiny footprint while staying MIT licensed is huge for independent builders who don't want to get locked into ecosystem wars.

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!

ThinHarness is a lightweight, minimal agent framework with clean code, built-in parallel LLM calls and powerful search tools, free of bloated extra layers for flexible custom business agent development.

custom-img
i write a16z speedrun scout checks withi...

This is exactly what the agent ecosystem needed. So many frameworks push you into their opinionated stack, but most projects just need focused primitives - filesystem tools, structured output, retries. The fact that ThinHarness gets you 5-10x framework coverage in a tiny footprint while staying MIT licensed is huge for independent builders who don't want to get locked into ecosystem wars.

Premium Products