Developer Tool / AI Coding Harness

llmisp

A local AI coding harness that turns business-rule specs into a constrained JSON AST, validates it, and compiles it into Clojure code while logging generation and repair artifacts.

Clear25/30
Useful24/30
Specific16/20
Complete15/20
llmisp screenshot

Why it was accepted

The page clearly describes a real AI-adjacent developer tool: a local code-generation harness for small models, with a defined workflow, validation layer, runtime requirements, and example commands. It shows enough detail for a useful directory listing and makes the project’s purpose and target users easy to understand.

Weakness

The snapshot does not show installation steps beyond command examples, a project license, release status, or proof of broader model support beyond the tested Gemma setup. It also leaves open how well the generated Clojure behaves on real workloads outside the five blind specs mentioned.

Review status

105 days ago #1445 ↓ -1

Last evaluated 105 days ago. Current rank #1445. Down 1 spot in the rankings.

Score history

80

Related listings

bdinfo-rs screenshot
92

Developer Tool / Media Analysis

A Rust Blu-ray disc analyzer that reimplements BDInfo for BDMV folders and ISO images, with CLI, desktop, and browser/WASM front ends.

WebLLM screenshot
#7 WebLLM
92

Developer Tool / AI SDK / In-browser LLM inference

WebLLM is a high-performance in-browser LLM inference engine that runs locally in the browser with WebGPU acceleration. It exposes an OpenAI-compatible API, supports streaming and JSON mode, and includes examples for building chat apps and browser extensions.

Molt screenshot
#31 Molt
90

Developer Tool / AI Agent Infrastructure

Molt is an open protocol for letting an AI agent make bounded purchases through disposable, single-use payment credentials. The repo includes a clear quickstart, MCP integration, a threat model, and a working test-mode demo.

Flightdeck screenshot
90

Developer Tool / AI Observability

Self-hosted observability and control plane for production and coding AI agents, with live timelines, fleet-wide feeds, token budgets, MCP allow/block rules, and support for Claude Code plus a Python sensor.