Apodex 1.1 ships 36B open-weight mini model with FrontierAgent, an open-source ReAct/Agent-Team CLI framework
kimmonismus · x · 2026-09-28
A thread by kimmonismus details the open-source side of Apodex 1.1:
- Model: Apodex-1.1-mini is a 36B open-weight model built for end-to-end research execution — preparing files, choosing methods, running analysis, fixing breakage, and verifying conclusions. Quantized variants (FP8, NVFP4, GPTQ-Int4, GGUF) are on Hugging Face.
- Framework: FrontierAgent (4.7k GitHub stars) is an open-source command-line TUI supporting ReAct and Agent Team workflows across files, search, and code. It runs on macOS and Linux with optional Docker and no preinstalled dependencies.
More from coding & agent
- Stop prompting LLMs for JSON: PowerShell module Jev routes with decision models — dfinke · 2026-11-16
- Baseten's Guide: Evaluate Open Models for Coding Agents on Your Own PRs — baseten · 2026-11-16
- Google Research open-sources PaperOrchestra, a multi-agent framework for writing AI papers — google-research · 2026-11-16
- ffmpeg-skill gives coding agents local video editing via 42 FFmpeg tools and MCP — kajisho5 · 2026-11-16
- ai-rulez author shows how a single success score hides MCP skill-discovery failure modes — Goldziher · 2026-11-16
- IndyDevDan argues small agent teams beat one mega-agent: the model isn't your edge — IndyDevDan · 2026-11-16