Alternatives
Products that do what Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens does
Hi HN, not sure if anyone would be interested, but just wanted to share that I've been maintaining my small tool called 'lowfat' that helps me filters some of my verbose CLI output. It's a single binary, works as an agent hook or a shell wrapper. It has a plugin system to customize filters per command. The idea is pretty simple: agents don't need the full kubectl get -o yaml or any 10k-line dump to make decisions. So that lowfat sits in between, strips the noise, and passes through what matters. Here's my real report after 2 months of personal use: lowfat history --all lowfat plugin…
- 1
- 2KR
I discovered that in LLM inference, keys and values in the KV cache have very different quantization sensitivities. Keys need higher precision than values to maintain quality. I patched llama.cpp to enable different bit-widths for keys vs. values on Apple Silicon. The results are surprising: - K8V4 (8-bit keys, 4-bit values): 59% memory reduction with only 0.86% perplexity loss - K4V8 (4-bit keys, 8-bit values): 59% memory reduction but 6.06% perplexity loss - The configurations use the same number of bits, but K8V4 is 7× better for quality This means you can run LLMs with 2-3× longer…
2025 · github.com
- 3
- 4BA
Hi HN! I'm Erik. We built Butter, an LLM proxy that makes agent systems deterministic by caching and replaying responses, so automations behave consistently across runs. - It’s a chat completions compatible endpoint, making it easy to drop into existing agents with a custom base_url - The cache is template-aware, meaning lookups can treat dynamic content (names, addresses, etc.) as variables You can see it in action in this demo where it memorizes tic-tac-toe games: https://www.youtube.com/watch?v=PWbyeZwPjuY Why we built this: before Butter, we were Pig.dev (YC W25), where we…
Oct 2025 · butter.dev
- 5AT
I recently built a small open-source tool to benchmark different LLM API endpoints — including OpenAI, Claude, and self-hosted models (like llama.cpp). It runs a configurable number of test requests and reports two key metrics: • First-token latency (ms): How long it takes for the first token to appear • Output speed (tokens/sec): Overall output fluency Demo: https://llmapitest.com/ Code: https://github.com/qjr87/llm-api-test The goal is to provide a simple, visual, and reproducible way to evaluate performance across different LLM providers, including…
2025 · llmapitest.com
- 6LP
Hello hacker news, I’m the maintainer of liteLLM() - package to simplify input/output to OpenAI, Azure, Cohere, Anthropic, Hugging face API Endpoints: https://github.com/BerriAI/litellm/ We’re open sourcing our implementation of liteLLM proxy: https://github.com/BerriAI/litellm/blob/main/cookbook/proxy-... TLDR: It has one API endpoint /chat/completions and standardizes input/output for 50+ LLM models + handles logging, error tracking, caching, streaming What can liteLLM proxy do? - It’s a central place to…
2023 · github.com
- 7BA
Hi HN, Erik here. Today we launch Butter, an OpenAI-compatible API proxy that caches LLM generations and serves them deterministically on revisit. Since April, we’ve been working on this concept of “muscle memory,” or deterministic replay, for agent systems performing automations. You may recall our first post in May, launching a python package called Muscle Mem: https://news.ycombinator.com/item?id=43988381 Since then, the product has evolved entirely, now taking the form of an LLM Proxy. For a deep dive into this process, check out:…
Oct 2025 · docs.butter.dev
- 8KM
I built kanban-md because I wanted a simple local task tracker that works well for the agent loop: drop tasks in, run multiple agents in parallel, avoid collisions, and observe progress easily. Tasks are just Markdown files (with YAML frontmatter) in a `kanban/` next to your code — no server, no DB, no API tokens. Simple, transparent, future-proof. What makes it useful for multi-agent workflows: - *Atomic `pick --claim`* so two agents don’t grab the same task. - *Token-efficient `--compact` output* (one-line-per-task) for cheap polling in agent loops. - *Skills included* -- just run…
Feb 2026 · github.com
- 9
- 10AL
Raymond here from Butter.dev, an LLM response cache built as a chat-completions proxy. Today we're launching a key feature for the platform: the ability to generalize on dynamic, templated inputs. Caching at the HTTP request level has the obvious problem of generalizability. Nearly no request is identical, due to templated variables (like names) and metadata (like timestamps), so exact-match cache lookups rarely hit. We solve this at Butter by using LLMs to detect dynamic content in requests and derive their inter-relationships, allowing the cache entry to be stored as a template + variables…
Jan 2026 · blog.butter.dev
- 11AL
Hey HN! After struggling with complex prompt engineering and unreliable parsing, we built L1M, a simple API that lets you extract structured data from unstructured text and images. curl -X POST https://api.l1m.io/structured \ -H "Content-Type: application/json" \ -H "X-Provider-Url: demo" \ -H "X-Provider-Key: demo" \ -H "X-Provider-Model: demo" \ -d '{ "input": "A particularly severe crisis in 1907 led Congress to enact the Federal Reserve Act in 1913", "schema": { "type": "object", "properties": { "items": { "type": "array", "items": { "type": "object", "properties": {…
2025 · l1m.io
- 12LT
Current AI-assisted CLI tools are often part of larger systems and work better on Linux. I built llm-term to address these. It's a Rust-based tool that compiles into a single binary file. You only need to download the binary, add it to your PATH, and configure your OpenAI key to get started. While llm-term offers an option for gpt-4o, it works great with gpt-4o-mini. So it's not costly. I appreciate any feedback or suggestions.
2024 · github.com
- 13UA
Hey HN! After using a combination of Unsloth and Axolotl a lot, and finding it generally painful to figure out the right performance tuning for things like batch sizing and multi-GPU sharding, I wrote a small Python lib that sets up known-good LoRA training configurations for Llama 3.1 8B and 70B Instruct, and includes helpers for distilling from larger models or training on serverless finetuning platforms, and includes a walkthrough for distilling DeepSeek-R1 into a Llama 3.1 8B LoRA... But you can use it for pretty much any finetuning task, not just distilling large models!
2025 · github.com
- 14RC
Hello HN! We're building a caching solution for LLMs (ChatGPT, Claude). By combining cutting-edge approaches, such as edge computing, prompt compression, vectorization, and others - it can reduce your AI bills by up to 10x and significantly lower response times. Key Features: - cost efficiency: our system stores frequent queries, reducing the number of upstream (paid) API calls - fast responses: with various nodes globally, we reduce latency by serving data from the nearest location - scalability: designed to handle increasing loads and data sizes without degrading performance. The cache…
2024 · edgematic.dev
- 15KC
As we all are, I've been experimenting with ways to reduce external saas spend, and continually bring traditionally external pieces of context (prs, docs, trello boards) into the one mono repo. I have toyed with a markdown todo list and setting claude/codex into a "ralph" loop previously, but always missed the web ui for organising, planning, and tracking things in progress. So codex and I build kanban-cli, an installable or npx-runnable cli util that takes one or more markdown files, and uses markdown headers and todo syntax to track and manage agentic tasks. Let me know your thoughts,…
May 2026 · github.com
- 16CC
If you had to build a context window manager in 24h, would you stick to the existing model or come up with something better? Here's what I did: 1. Built a proxy that intercepts Codex's calls to OpenAI and rewrites them on the fly. 2. Replayed 3,807 rounds of SWE-bench Verified traces through it: avg prompt 44k → 6k tokens (-87%). 3. Posted it to HN to get the next reduction applied to my confidence interval — starting with the inevitable "How about accuracy?" npx -y pando-proxy · github.com/human-software-us/pando-proxy
Apr 2026 · npmjs.com
- 17OA
Hi HN, we're Kiran and Vijay! Over the past two years, we have built a columnar storage engine for observability: logs, metrics, and traces. Today, it's exciting for us to show what we've built on top of that foundation: LLM Agent Observability. Given how non-deterministic agents are, storing all traces without sampling was critical for us. But these traces tend to be in the MBs, sometimes GBs - we needed to store them inexpensively. We also needed the queries and analyses to be fast. To meet both these goals, we store them in S3 in our own parquet-like file format, and query them using AWS…
Jul 2026 · oodle.ai
- 18KC
Hello HN, Ever since agents have become increasingly common in development, I've been scratching my head as to how to control their randomness. Recently, I decided to emulate an issue-tracking and project-management tool for agent-driven workflows. Kanban is a Rust-based coordination layer designed to provide a feature-rich terminal interface and enforce rigorous workflows. It aims to be versatile and extendable, made to be tailored to any preferred flow. It comes with full git integration and guardrails such that only what truly benefits a project can go through. The workflow boils down to…
May 2026 · codeberg.org
- 19PS
What PII-Shield does: It's a K8s sidecar (or CLI tool) that pipes application logs, detects secrets using Shannon entropy (catching unknown keys like "sk-live-..." without predefined patterns), and redacts them deterministically using HMAC. Why deterministic? So that "pass123" always hashes to the same "[HIDDEN:a1b2c]", allowing QA/Devs to correlate errors without seeing the raw data. Key features: 1. JSON Integrity: It parses JSON, sanitizes values, and rebuilds it. It guarantees valid JSON output for your SIEM (ELK/Datadog). 2. Entropy Detection: Uses context-aware entropy…
Feb 2026 · github.com
- 20AS
There are plenty of good tools for load testing such as JMeter, Minigun, and plenty more - but they all have their own set of options to learn. I built this one to support a simpler workflow where you just paste your curl request (or other cli command) after your `spam` config (literally just `spam -r 2 -- curl www.google.com). It's pretty barebones but I'm 100% going to use it in my day to day - figured I'd share it here if it helped anyone else!
2023 · github.com
- 21KP
I thought it'd be interesting to use Linux PSI (Pressure Stall Information) for an LLM runtime to trim the KV cache. This is mainly useful imo for edge devices like the Jetson Orin super nano kit which have unified memory. I haven't benched much, but plan to do so more over time and see if I can make a real use of it as I run local LLMs. Let me know if it makes sense :P (I of course vibed this idea)
Jun 2026 · github.com
- 22CB
I built a small benchmark to test CLI coding agents on blind bug detection. A challenger agent injects bugs and writes ground truth (`bugs.json`). A different reviewer agent audits the repo without seeing ground truth, and an LLM matcher scores bug-to-finding assignments. Current run: 50 repos, 150 challenges, 450 reviews, 2,603 injected bugs. Weighted detection: Claude 58.05%, Codex 37.84%, Gemini 27.81%. LLM-judge benchmarks are easy to get wrong, so I’d really appreciate critical feedback on benchmark fairness, scoring/matching methodology, and obvious failure modes I’m missing. Full…
Feb 2026 · github.com
- 23SC
I created a tool that consolidates information from the following inputs: GitHub repository URL (e.g., https://github.com/jimmc414/onefilellm) arXiv abstract URL (e.g., https://arxiv.org/abs/2401.14295) Local folder path (e.g., C:\python\PipMyRide) Youtube video URL (e.g., https://www.youtube.com/watch?v=KZ_NlnmPQYk) Webpage URL (e.g., https://llm.datasette.io/en/stable/) It outputs the repo, web documentation, arXiv paper or YT transcript to a text file and the clipboard, displaying a token count. It also…
2024 · github.com
- 24AC
Multi-tier exact-match cache for AI agents backed by Valkey or Redis. LLM responses, tool results, and session state behind one connection. Framework adapters for LangChain, LangGraph, and Vercel AI SDK. OpenTelemetry and Prometheus built in. No modules required - works on vanilla Valkey 7+ and Redis 6.2+. Shipped v0.1.0 yesterday, v0.2.0 today with cluster mode. Streaming support coming next. Existing options locked you into one tier (LangChain = LLM only, LangGraph = state only) or one framework. This solves both. npm:…
Apr 2026
Ranked by how close each launch is in meaning, then by votes. Refine with a description →