Alternatives
Products that do what Zenith: sota harness for normal models to beat Fable on FrontierSWE does
- 18F
Hi HN! I'm just sharing a project I've been working on during the LLM Efficiency Challenge - you can now finetune Llama with QLoRA 5x faster than Huggingface's original implementation on your own local GPU. Some highlights: 1. Manual autograd engine - hand derived backprop steps. 2. QLoRA / LoRA 80% faster, 50% less memory. 3. All kernels written in OpenAI's Triton language. 4. 0% loss in accuracy - no approximation methods - all exact. 5. No change of hardware necessary. Supports NVIDIA GPUs since 2018+. CUDA 7.5+. 6. Flash Attention support via Xformers. 7. Supports 4bit and 16bit…
2023 · github.com
- 2IV
The video demo runs a 7b Model on a normal gaming GPU. I think it already works quite well (accounting for the limited hardware power). :)
2024 · github.com
- 3
Open-source unified interface for agent harnesses
21d ago · harnessrouter.ai
- 4AA
2019 · adventurekeep.com
- 5DG
2021 · dragonruby.org
- 6BH
Hey HN, We got tired of browser frameworks restricting the LLM, so we removed the framework and gave the LLM maximum freedom to do whatever it's trained on. We gave the harness the ability to self correct and add new tools if the LLM wants (is pre-trained on) that. Our Browser Use library is tens of thousands of lines of deterministic heuristics wrapping Chrome (CDP websocket). Element extractors, click helpers, target managemenet (SUPER painful), watchdogs (crash handling, file downloads, alerts), cross origin iframes (if you want to click on an element you have to switch the target first,…
Apr 2026 · github.com
- 7MA
hi all, I've always wanted to make my own game, but couldn't afford a thousand-dollar adobe (flash+photoshop) license. I'm not a talented programmer, have no degree in CS. But I understand some elements of design. So I got me a copy of ImpactJS, and after about 5 months of steep learning curve (at least for me), I managed to come up with a game. I also integrated it with a highscore and badge system, similar to what you get at Kongregate. You need to login with Google/OpenID to earn badges/scores. link is: http://www.hotbazooka.com/privatejoe hope to hear some feedback/questions from you guys!
2011 · hotbazooka.com
- 8OS
Hi I'm Dan from Elodin, making an open source real-time capable flight software simulation. For AI Grand Prix contestants, the wait for the Round 1 virtual qualifier simulation has been grueling. If you’re competing, check out our simulation harness to tide you over, built to match the published competition constraints and message format. It runs against real Betaflight, which we learned requires at least 1000 sensor samples per second to run real-time correctly. The competition warranted introducing a new feature to generate the camera sensor directly in the simulation loop. Typically…
May 2026 · elodin.systems
- 9
- 10OA
Hi HN, we built world-model-optimizer, an open source tool to continually improve a specialized model for an agent. It does this by simulating production tool responses through text world modeling (similar to QwenAgentWorld, summary here https://x.com/silennai/status/2073887455884058814). We can then use this to train a router for frontier, OS, and local models (use defaults or pick which ones to optimize against). wmo ingests agent traces, builds the simulation, embeds the traces, runs different models you choose against the simulation scenarios, and then uses a KNN…
Jul 2026 · github.com
- 11SA
2018 · github.com
- 12
Same model. Similar pass rates. 17.5x cost differences across 12 harness configurations.
4d ago · frontierharness.org
- 13IH
I started off with a simple goal: port the game Soldat to Typescript. I ended up not only with the game, but with a full system to train AI bots to play my own game, building a neural net to train new bot AIs from tens of thousands of simulated matches with different strategies. It also runs live all the time on my website and has a news dashboard and you can replay any game exactly. It all was a very fun way to dig into Fable's capabilities. The bill if I had done this with API billing? Nearly $2000.
Jun 2026 · soldat.bobbby.online
- 14RA
Hi there, looking for feedback on my new project "Featherless.AI" The idea is to allow users to run all the models on hugging face instantly. Via the OpenAI API compatible endpoint. Why? Because its a real chore to download models and spin up GPUs, especially if you want to test multiple models. Not to mention GPUs cost multiple dollars an hour to rent. And if we want more people to use open source AI, we got to make it easier for them to try and play with all of them. So what if instead of spinning up dedicated GPUs per model (which is what every provider is doing) We can startup a LLM…
2024 · featherless.ai
- 15PT
2015 · github.com
- 16UM
I'm building Guildly, a Slack-like interface where you can run a company of AI employees. I recently used Fable to revamp the whole website into a cool retro pixel style.
Jul 2026 · tryguildly.com
- 17AA
2012 · wwwtyro.github.com
- 18
Hey HN! We are building HarnessRouter, a canonical API for running Codex, Claude Code, Hermes, and other managed agent harnesses as your product backend. Before building HarnessRouter, I used to build our own agent harness for our products. I tried LangGraph, agent SDKs from different vendors, pydantic, LLM tool use / function call, and so on. It's a very heavy lifting engineering effort, and I am disappointed about the agent deliveries compared to what Codex, CC can deliver. That changed my mindset. The frontier labs and famous open source communities are already putting so much…
20d ago · github.com
- 19IB
Hey HN. I built an AI agent harness over the past few months and I'm open sourcing it today. Some context on why. I've been building with Claude Code daily using this harness. It orchestrates multiple AI agents as a team, with a dashboard, chat, kanban board, the works. I used it to build a full SaaS product (MyUpMonitor, https://myupmonitor.com) in about 24 hours of focused coding. Then yesterday Anthropic announced Mythos and decided to keep it behind closed doors. Meanwhile I'm paying for Claude and I can't access their best model. I don't think that is nice at all... So I'm…
Apr 2026 · github.com
- 20
Around 3 months ago, we were thinking why none of the iPhone apps running an LLM are built as a full harness (as in inference + agentic loop + context management + tools + MCP servers and etc.). It became more interesting when we noticed even the new Siri is not fully on device (and not available in EU for that matter). Having built a few agentic products around a custom harness in the past, we thought this shouldn't be that hard. well, we underestimated how "dumb" a 4B model can be, especially when it comes to tool calling. :D We tried 8 different models and we settled on Qwen 3.5 4B and we…
18d ago · orvena.app
- 21CA
Hey folks, we created a ChatGPT alternative for anyone to try out LLaMA models and benchmark responses across OpenAI's models and other open source models. Would love some feedback! No data is being used for retraining models.
2023 · chat.nbox.ai
- 22
Anthropic's most capable model, now available to everyone
Jun 2026 · anthropic.com
- 23QG
I've found the most engaging way to practice techniques for AI-assisted development and test models is to build fun side projects in vanilla JS. I spent many hours playing (and studying and editing) QBasic Gorillas, and this is a vanilla JS implementation using Fable and Opus. Play 1-on-1 hotseat or against the computer. A bit of extra camera snazz as well.
Jul 2026 · gameswithtony.com
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →