Apodex 1.1: 35B Open-Source Model Matches 1T-Parameter Systems on Agentic Tasks
Div_pradeep · x · 2026-08-28
Apodex 1.1 is a new model family designed to scale agentic intelligence for professional work. The developers claim that its 35B open-weights model delivers performance nearly matching trillion-parameter frontier systems on complex agentic tasks.
Key features include:
- Frontier-level Intelligence: Capable of handling complex professional work, scientific research, financial analysis, and deep search.
- Asynchronous Agent Teams: Can break down complex tasks, coordinate multiple agents in parallel, and continuously integrate findings, allowing users to step in and guide the workflow.
- Local-first: Focuses on local deployment with practical Agent Team capabilities.
The model emphasizes step-by-step reasoning and verification to produce "verified briefs" rather than simple chat replies. Open weights are available on Hugging Face, and the FrontierAgent framework is on GitHub.
More from coding & agent
- A versioned bootstrap loader pattern for keeping AI-generated code always shippable — NickPassig · 2026-10-15
- Amazon blocks AI shopping agents; Maritime offers $1/month Android MCP workaround — Scobleizer · 2026-10-15
- Dev vibe-codes open-source newsletter platform, 83% cheaper than Beehiiv from $19/mo — marclou · 2026-10-15
- ERP AI launches Proto: 'headless SaaS' business software built for AI agents — Aiden_Tech_Ai · 2026-10-15
- Engineering managers need deep reading, not just agent summaries: 5 recommended resources — rseroter · 2026-10-15
- Adding motion graphics with just a prompt: the Claude Motion x ElevenLabs MCP workflow — CurieuxExplorer · 2026-10-15