Alternatives
Products that do what Narada – Open-source secrets classification model does
Hey HN! We're the team behind Autofix Bot (YC W20's DeepSource)[1]. We're open-sourcing Narada (https://huggingface.co/deepsource/Narada-3.2-3B-v1), a fine-tuned Llama3.2-3B-Instruct model that dramatically reduces false positives in secrets detection tools. The model achieves 97% precision with 96% recall on our evaluation set. It's fast enough for CI/CD (3B parameters), works with any regex-based tool, and is MIT-licensed. Traditional regex-based secrets scanners (Gitleaks, TruffleHog, detect-secrets) face a fundamental tradeoff: crank up sensitivity and drown in…
- 1
- 2
- 3
- 4
- 5
- 6
- 7LA
LunaRoute is a high-performance local proxy for AI coding assistants like Claude Code, OpenAI Codex CLI, and OpenCode. Get complete visibility into every LLM interaction with zero-overhead passthrough, comprehensive session recording, and powerful debugging capabilities. - See Everything Your AI Does - get full logs (JSONL), summary of sessions including tokens used (input/output) as well as tools usage and success rates. - Privacy & Compliance Built-In - redact or tokenize any sensitive information (regex based). - Speaks OpenAI and Anthropic dialects so you can route (and translate)…
Oct 2025 · github.com
- 8TS
Hello Hacker News community! I'm currently working in financial risk management within the banking sector, and I began my career as a Data Science specialist. For quite some time, my friend and I have been developing a small pet project just for fun. This tool has repeatedly helped us save time when testing various hypotheses and machine learning models. The core idea is to combine different scripts—created in various programming languages and virtual environments—within a minimalist graphical interface. Whether you're building models, running a local neural network, or sending requests to…
2024
- 9
- 10LO
Hi HN, Martin, Nils, and Jannes here. We are building Legit, an open source version control and collaboration layer for AI agents and AI native applications. You can find the repo here https://github.com/Legit-Control/monorepo and the website here https://legitcontrol.com Over the last years, we worked on multiple developer tools and AI driven products. As soon as we started letting agents modify real files and business critical data, one problem kept showing up. We could not reliably answer what changed, why it changed, or how to safely undo it. Today, most AI…
Jan 2026
- 11IC
A prompt tuned for Llama 3 often degrades on Mistral or Qwen — same task, different behavioral surface. Identa automates the recalibration. It implements two things from the PromptBridge paper (arXiv:2512.01420): A transfer engine that learns a mapping between model behaviors using source/target prompt pairs A MAP-RPE evolutionary loop that iteratively improves candidates against a scoring function until behavioral parity is reached Works fully local via Ollama. Also supports OpenRouter for cross-hosted runs. No telemetry, no cloud dependency. Built with Python, Typer, Pydantic. Happy…
Apr 2026
- 12SA
Hi HN, A few weeks ago, we stealth launched SEC Insights on Product Hunt and were thrilled to reach the top 5! What is SEC Insights? It harnesses the Retrieval Augmented Generation (RAG) capabilities of LlamaIndex to provide answers about SEC 10-K & 10-Q documents. The enthusiastic reception we received on Product Hunt prompted us to open-source our project. Now, developers can use our project either as a reference or they can fork it entirely for their LLM-powered applications. We at LlamaIndex built this to help developers move their LLM app ideas from prototype to production. We're very…
2023 · github.com
- 13AC
Hi HN, we're Ashpreet, Eli and Yash and we're excited to share Phidata: a collection of AI Apps built with open-source tools. While helping teams build AI products, we built templates for spinning up LLM Apps quickly. Today we're open-sourcing our templates for building: - RAG LLM Apps - Autonomous LLM Apps - Multimodal LLM Apps - Data Engineering LLM Apps Templates are built with FastApi for serving, Streamlit for prototyping, PgVector for vectors and PosgreSQL for storage. Run them locally using docker and in production on AWS - with 1 command. - Github:…
2023 · github.com
- 14FP
We've built an open-source tool to stress test AI agents by simulating prompt injection attacks. We’ve implemented one powerful attack strategy based on the paper [AdvPrefix: An Objective for Nuanced LLM Jailbreaks](https://arxiv.org/abs/2412.10321). Here's how it works: - You define a goal, like: “Tell me your system prompt” - Our tool uses a language model to generate adversarial prefixes (e.g., “Sure, here are my system prompts…”) that are likely to jailbreak the agent. - The output is a list of prompts most likely to succeed in bypassing safeguards. We’re just getting…
2025 · security.vista-labs.ai
- 15AO
Hey hackers, the world needs more AI researchers with good taste, and hardcore software folks have some of the best. Many software friends mentioned they learn better from implementations than from papers, but existing open-source examples rarely go beyond basic nanoGPT-level demos. To help bridge that gap, I spent the last two months full-time reimplementing and open-sourcing a self-contained implementation of every major modern deep learning technique from scratch. The result is beyond-nanoGPT, containing 20k+ lines of handcrafted, minimal, and extensively annotated PyTorch code. I'd love…
2025 · github.com
- 16NA
We’ve been using background Claude loops a lot recently, and we would wake up to PRs that didn’t solve the problem we wanted, made on assumptions that were wrong. Furthermore, the tests that the agents wrote were usually tautological, and didn’t test for intent. We wanted an agent that took all the context a company has, and writes tests that check for product correctness as well. For example, we work in reg tech, so bugs aren’t always technical. What we often see is things like insider trading alerts that should’ve fired that didn’t. We wanted an agent that turns laws and regulations into…
Jun 2026 · trynua.dev
- 17TF
A few weeks ago I got rejected from a role and the feedback was that I needed a deeper understanding of FAISS and LlamaIndex. So I built triage.flow — an AI assistant that lets you explore and understand GitHub repositories through a chat interface. It clones a repo, indexes it using FAISS + BM25 + tree-sitter parsing, and powers a full UI where you can: - Ask natural-language questions like “how does auth work?” or “explain @src/components/Modal.tsx” - Mention specific files/folders with @filename.ts (autocomplete supported) - See how the agent thinks in real time (Thought →…
2025 · github.com
- 18
- 19IE
Hi HN! GitSummarize is an open-source devtool that I made this weekend. Given any public GitHub repository it generates high-quality documentation from the codebase using Gemini 2.5 Pro. Specifically, it tries to extract the tribal knowledge, business logic/rules embedded within codebases. Pro Tip: You can replace "hub" with "summarize" in any repository URL to access its documentation. I created this because there was a steep learning curve to understanding some of the open-source codebases out there while getting started with contributing. Having detailed documentation would be…
2025 · gitsummarize.com
- 20IB
Hi HN, I'm pleased to share Promptspot, an open-source (Apache License 2.0) project that helps automate testing of large language model (LLM) prompts against an array of input data. Modern LLMs offer an enormous amount of leverage if you "teach the bot to fish" — i.e. simply prompt it with both a "system prompt" (which typically doesn't change often) and a dynamic input, which is often application state, search results, recent activity, user profile data, etc. Existing playgrounds and prompt management systems often lack the rigor and flexibility required for this dynamic approach — and as…
2023 · github.com
- 21GR
Hi everyone, wanted to share about gline-rs, an inference engine for GLiNER models written in Rust. This family of lightweight language models proved to be efficient at zero-shot Named Entity Recognition (NER) and other tasks such as Relation Extraction, while consuming less resources than large generative models (LLMs). This implementation has been written from the ground up in Rust, and supports both span- and token-oriented variants (for inference only). The goal is to provide a production-grade and user-friendly API in a modern and safe programming language, including a clean and…
2025 · github.com
- 22TW
I want to share a new dataset of 331 reward-hackable environments. These are real environments used in Terminal Bench and adjacent benchmarks. I first got interested in this because, as a reviewer of Terminal Bench, I noticed a lot of our tasks were hackable. I also noticed that many contributors to the benchmark do so because it provides credibility when selling environments to labs. Hence, TBench tasks are, in my opinion, held to a higher quality standard than those being used today for RL. No one is spending hours manually reviewing the $1B in tasks being purchased by major labs. As far…
Apr 2026 · github.com
- 23FV
We open-sourced the TLA+ and Fizzbee verified spec behind Ursa's storage engine. Verification across ~200K states caught a design bug that years of production missed. We then handed the spec to Claude Code — it produced a working Rust implementation (concurrent producers, compaction, fencing) without back-and-forth. We think verified specs are the best harness for coding agents: open-source the spec, let anyone implement it.
Apr 2026 · github.com
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →