Ideas Lab

A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

I shipped a wiki layer for AI agents that uses markdown + git as the source of truth, with a bleve (BM25) + SQLite index on top. No vector or graph db yet.It runs locally in ~/.wuphf/wiki/ and you can git clone it out if you want to take your knowledge with you.The shape is the one Karpathy has been circling for a while: an LLM-native knowledge substrate that agents both read from and write into, so context compounds across sessions rather than getting re-pasted every morning. Most implementations of that idea land on Postgres, pgvector, Neo4j, Kafka, and a dashboard.I wanted to go back to the basics and see how far markdown + git could go before I added anything heavier.What it does: -> Each agent gets a private notebook at agents/{slug}/notebook/.md, plus access to a shared team wiki at team/.-> Draft-to-wiki promotion flow. Notebook entries are reviewed (agent or human) and promoted to the canonical wiki with a back-link. A small state machine drives expiry and auto-archive.-> Per-entity fact log: append-only JSONL at team/entities/{kind}-{slug}.facts.jsonl. A synthesis worker rebuilds the entity brief every N facts. Commits land under a distinct "Pam the Archivist" git identity so provenance is visible in git log.-> [[Wikilinks]] with broken-link detection rendered in red.-> Daily lint cron for contradictions, stale entries, and broken wikilinks.-> /lookup slash command plus an MCP tool for cited retrieval. A heuristic classifier routes short lookups to BM25 and narrative queries to a cited-answer loop.Substrate choices: Markdown for durability. The wiki outlives the runtime, and a user can walk away with every byte. Bleve for BM25. SQLite for structured metadata (facts, entities, edges, redirects, and supersedes). No vectors yet. The current benchmark (500 artifacts, 50 queries) clears 85% recall@20 on BM25 alone, which is the internal ship gate. sqlite-vec is the pre-committed fallba

Hacker News4mo agoToolAI

AgentSwift – Open-source iOS builder agent

I'm working on a coding agent for building iOS apps. It's built on openspec and xcodebuildmcp. It's free and open source.

Hacker News4mo agoToolDev

leaf – a terminal Markdown previewer with a GUI-like experience

Hacker News4mo agoToolDesign & Creative

SKIP

42FL score

Rocky – Rust SQL engine with branches, replay, column lineage

Hi HN, I'm Hugo. I've been building Rocky over the past month, shipping fast in the open. The binary is on GitHub Releases, `dagster-rocky` on PyPI, and the VS Code extension on the Marketplace. I held off on a broader announcement until the trust-system surface was coherent enough to talk about as one thing. The governance waveplan — column classification, per-env masking, 8-field audit trail on every run, `rocky compliance` rollup, role-graph reconciliation, retention policies — landed end-to-end last week in engine-v1.16.0 and rounded out in v1.17.4 (tagged 2026-04-26). That's the milestone I'd been waiting for.The pitch: keep Databricks or Snowflake. Bring Rocky for the DAG. Rocky is a Rust-based control plane for warehouse pipelines. Storage and compute stay with your warehouse. Rocky owns the graph — dependencies, compile-time types, drift, incremental logic, cost, lineage, governance. The things your current stack can't give you because it doesn't own the DAG.A few things I think are interesting:- Branches + replay. `rocky branch create stg` gives you a logical copy of a pipeline's tables (schema-prefix today; native Delta SHALLOW CLONE and Snowflake zero-copy are next). `rocky replay <run_id>` reconstructs which SQL ran against which inputs. Git-grade workflow on a warehouse.- Column-level lineage from the compiler, not a post-hoc graph crawl. The type checker traces columns through joins, CTEs, and windows. VS Code surfaces it inline via LSP.- Governance as a first-class surface. Column classification tags plus per-env masking policies, applied to the warehouse via Unity Catalog (Databricks) or masking policies (Snowflake). 8-field audit trail on every run. `rocky compliance` rollup that CI can gate on. Role-graph reconciliation via SCIM + per-catalog GRANT. Retention policies with a warehouse-side drift probe.- Cost attribution. Every run produces per-model cost (bytes, duration). `[budget]` blocks in `rocky.toml`;

Hacker News4mo agoToolAI

Adblock-rust Manager – Firefox extension to enable the Brave ad blocker

Firefox 149 ships adblock-rust (Brave's Rust engine, MPL-2.0) completely disabled with no UI. It's controlled by two about:config prefs with no WebExtension API, so you can't touch them programmatically from a standard extension.This extension gives it a UI: ETP toggle (via browser.privacy API, instant), filter list manager with clipboard helpers for the manual about:config steps, and 8 preset lists. You can also add your own if you so desire.

Hacker News4mo agoToolDev

SKIP

42FL score

A terminal spreadsheet editor with Vim keybindings

While speccing out this spreadsheet tool, I realized that I never had to think about the keybindings. It all just came naturally from Vim. Normal/insert/visual modes, hjkl navigation, dd/yy/p, :w, :q. The usual muscle memory works.It supports CSV/TSV import and export, and a native .cell format that preserves formulas. The formula engine handles SUM, AVERAGE, COUNT, MIN, MAX, and IF with range references.The codebase is a Cargo workspace: a pure cell-sheet-core library (no TUI dependency) and a cell-sheet-tui crate on top of ratatui. Early days, but it's usable.To try it out: cargo install cell-sheet-tuiFeedback of any kind is greatly appreciated!

Hacker News4mo agoToolDev

Free background removal tool with advanced options

Users seek accessible background removal for images but existing free tools (Photoshop, Canva) lack depth or are paywalled. A specialized free tool with batch processing, transparency control, and API access serves creators, marketers, and ecommerce. [Google Search suggestion]

Google Trends4mo agoToolDesign & CreativeUS

Fast batch image resizer with format conversion

Creators, social media managers, and ecommerce sellers need to resize images at scale but free tools are slow or ugly. A fast batch resizer with templates for different platforms (Instagram, Shopify, etc.) saves hours. [Google Search suggestion]

Google Trends4mo agoToolDesign & CreativeUS

Room Layout Visualization & Planning Tool

Help users digitally plan room rearrangement with furniture placement, 2D/3D visualization, and measurement tools before moving heavy items physically. [Google Search suggestion]

Google Trends4mo agoToolProductivityUS

Personal Injury Case Management & Attorney Matching

Solo developers could build a platform connecting injury claimants with attorneys, tracking case milestones, and managing claim documentation. Current solutions fragmented across regional practices. [Trending: "personal injury attorneys" with 100+ searches in US]

Google Trends4mo agoToolLegalUS

Free PDF redaction tool for sensitive documents

Users need to redact PII from PDFs (contracts, resumes, sensitive docs) but Adobe charges, and free tools are clunky. A clean, fast redaction tool with batch processing solves this for remote workers, lawyers, and compliance teams. [Google Search suggestion]

Google Trends4mo agoToolProductivityUS

Batch PDF merger with compression and metadata control

Users combine PDFs regularly but free tools are slow, ads-heavy, or lose formatting. A fast, clean PDF combiner with compression, page reordering, and batch mode solves workflow friction for students, remote workers, and document-heavy teams. [Google Search suggestion]

Google Trends4mo agoToolProductivityUS

SKIP

42FL score

Frictionless Point-of-Sale Authentication

Merchants need faster, more secure payment authentication at checkout. Biometric payment methods (fingerprint) offer speed and security benefits over traditional cards.

YC Graveyard12y agoToolFintech

Photo Editing Workflow Optimization

Professional photographers need fast, intuitive photo editing and organization tools. Batch processing and one-click enhancement workflows save hours per shoot.

YC Graveyard11y agoToolConsumer

A new benchmark for testing LLMs for deterministic outputs

When building workflows that rely on LLMs, we commonly use structured output for programmatic use cases like converting an invoice into rows or meeting transcripts into tickets or even complex PDFs into database entries.The model may return the schema you want, but with hallucinated values like `invoice_date` being off by 2 months or the transcript array ordered wrongly. The JSON is valid, but the values are not.Structured output today is a big part of using LLMs, especially when building deterministic workflows.Current structured output benchmarks (e.g., JSONSchemaBench) only validate the pass rate for JSON schema and types, and not the actual values within the produced JSON.So we designed the Structured Output Benchmark (SOB) that fixes this by measuring both the JSON schema pass rate, types, and the value accuracy across all three modalities, text, image, and audio.For our test set, every record is paired with a JSON Schema and a ground-truth answer that was verified against the source context manually by a human and an LLM cross-check, so a missing or hallucinated value will be considered to be wrong.Open source is doing pretty well with GLM 4.7 coming in number 2 right after GPT 5.4.We noticed the rankings shift across modalities: GLM-4.7 leads text, Gemma-4-31B leads images, Gemini-2.5-Flash leads audio.For example, GPT-5.4 ranks 3rd on text but 9th on images.Model size is not a predictor, either: Qwen3.5-35B and GLM-4.7 beat GPT-5 and Claude-Sonnet-4.6 on Value Accuracy. Phi-4 (14B) beats GPT-5 and GPT-5-mini on text.Structured hallucinations are the hardest bug. Such values are type-correct, schema-valid, and plausible, so they slip through most guardrails. For example, in one audio record, the ground truth is "target_market_age": "15 to 35 years", and a model returns "25 to 35". This is invisible without field-level checks.Our goal is to be the best general model for deterministic tasks, and a key aspect of determinism is a con

Hacker News4mo agoToolAI

I've built a nice home server OS

ohai!I've released Lightwhale 3, which is possibly the easiest way to self-host Docker containers.It's a free, immutable Linux system purpose-built to live-boot straight into a working Docker Engine, thereby shortcutting the need for installation, configuration, and maintenance. Its simple design makes it easy to learn, and its low memory footprint should make it especially attractive during these times of RAMageddon.If this has piqued your interest, do check it out, along with its easy-to-follow Getting Started guide.In any event, have a nice day! =)

Hacker News4mo agoToolAI

Waiting for LLMs Suck – Give your user a game

Give your user a game while they wait for the LLM to return a result.

Hacker News4mo agoToolAI

Anyone want to collaborate on a local-first AI-based research assistant

Hi HN Community, I'm Venkatram, a sophomore who's on a mission to build a local alternative to proprietary third-party AI-based research assistants.The idea is to turn documents into researchable assets that contain as much as information as the original information does, but it's more reusable.Well, quite frankly, this is still under a WORK IN PROGRESS, so i'm still figuring on how it can be properly used, and I got to be honest here, i definitely need some help to build this, so if you wish, you are welcome!TlDR: NotebookLM, but Locally with your OWN AI ModelGithub: https://github.com/venkatram-s/gigabook-lm

Hacker News4mo agoToolAI