Show HN: Local LLM code-generation with Gemma 4 e2B via JSON AST to Clojure
The article discusses a local code-generation harness designed to convert text specifications into Clojure programs using the Gemma 4 E2B model. It emphasizes the use of JSON AST fragments for generating code, which are validated and compiled into Clojure source. Additionally, the harness supports generating Java Swing applications and includes various validation and logging features.
- ▪The harness runs a local Gemma 4 E2B GGUF model through llama-server.
- ▪It validates generated JSON AST using various checks and compiles it into Clojure source.
- ▪The system can also generate simple native Java Swing programs with a focus on deterministic GUI actions.
Hacker News (AI / LLM) files mainly under ai. We currently carry 2,776 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/quadracollision/llmisp |
| Publication time | Tue, 19 May 2026 17:53:20 +0000 |
| Retrieval time | 2026-05-19T18:09:57.887Z |
| Last seen | 2026-05-19T18:09:57.887Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | gMdl2UtQfRei |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
JSON AST Agent Harness This project is a local code-generation harness for turning text specs into Clojure programs. The validated local setup was tested with Gemma 4 E2B GGUF served by llama.cpp. Other models may work, but they are untested. The core idea is to stop asking a small local model to write full source code directly. Instead, the model emits constrained JSON AST fragments. The harness validates those fragments, assembles larger structures programmatically, lowers the accepted AST to Clojure, and records every generation/repair artifact in SQLite. What It Does Runs a local Gemma 4 E2B GGUF model through llama-server. Can target another OpenAI-compatible chat endpoint experimentally. Uses a planner pass to derive a sanitized contract from a text spec.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.