harness-hub
harness-hub is A collection of models trained with RL on specific adapters for more efficient agentic development. It is ranked #128 on the AI Radar, in AI agents, first seen 7 days ago and shared in 8 posts (119.9k views).
LFM2.5-24B Harness adapters - a harness-hub Collection Hugging Face Log In Sign Up harness-hub 's Collections LFM2.5-24B Harness adapters LFM2.5-24B Harness adapters updated about 2 hours ago A collection of models trained with RL on specific adapters for more efficient agentic development Upvote 5 Sort: Collection harness-hub/LFM2.5-24B-A2B-pi Updated about 2 hours ago • 3 harness-hub/LFM2.5-24B-A2B-claude-code Updated about 2 hours ago • 1 harness-hub/LFM2.5-24B-A2B-pi-GGUF 18.7M • Updated about 2 hours ago • 2 harness-hub/LFM2.5-24B-A2B-claude-code-GGUF 18.7M • Updated about 2 hours ago • 1 Upvote 5 +1 Sort: Collection Share collection…
What people said about harness-hub on X
LFMs are built to be customized. We think specialized intelligence is what enables more than half of enterprise AI usecases with predicable economics. This is an incredible work by the @huggingface team on tuning our LFM2.5-24B-A2B for more efficient agentic behavior in opensource harnesses. 🤗
— @liquidai, 6 days ago · 402 likes · see the post
LFM2.5-24B adapters for Pi and Claude Code! We release LoRA adapters trained on top of LFM2.5-24B - more efficient agentic development on opensource harnesses (up to 40% less tool calls on Pi!)! https://huggingface.co/collections/harness-hub/lfm25-24b-harness-adapters
— @yb2698, 7 days ago · 230 likes · see the post
👀👀👀
— @Teknium, 4 days ago · 268 likes · see the post
Alternatives to harness-hub
- Z.ai — chief scientist Jie Tang just revealed the training pipeline behind the upcoming GLM-5.5 (32B, 122B, and 256B) during…
- Console by Nace.AI — Cloud Inference
- dsh-superagent-prototype — DeepSeek open-sourced the design behind its always-on 'Super-agent': no chat window, and reportedly nearly half the…
- REA for Growth — 4,000+ data endpoints, one key.
- Muse — We've now paid out more than $1M in @muse bug bounties. That includes $300,000 to a security researcher who found the…
- Simulations — Test agent changes against real production scenarios to understand their impact on behavior, latency, and cost before…
harness-hub in numbers
- Rank on the AI Radar: #128 of 10410
- Shared in 8 posts by 7 accounts: @liquidai, @yb2698, @Teknium, @NFT_Chen
- 119.9k views on those posts
- First seen 7 days ago, last shared 4 days ago
- Pricing seen by AGK Intelligence: not stated
- Market: AI agents
FAQ
What is harness-hub?
A collection of models trained with RL on specific adapters for more efficient agentic development It was first shared on X 7 days ago and is ranked #128 on the AI Radar.
Is harness-hub free?
Pricing is not stated on the page we read.
Who shared harness-hub?
7 accounts on X, including @liquidai, @yb2698, @Teknium, in 8 posts totalling 119.9k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:05 UTC. Full method.