Launching today
LogiCoal

LogiCoal

AI multi-agent coding assistant for your terminal

28 followers

LogiCoal is an AI-powered CLI coding assistant with multi-agent orchestration, smart model routing, and deep codebase understanding. Free for macOS, Windows, and Linux.
LogiCoal gallery image
LogiCoal gallery image
LogiCoal gallery image
Free
Launch Team / Built With
Anima - OnBrand Vibe Coding
Design-aware AI for modern product teams.
Promoted

What do you think? …

Brandon Moore
Hey Product Hunt! I built LogiCoal out of frustration with the current state of AI coding tools. Context windows are too small — LogiCoal supports 128K with autocompact (256K coming soon). Most tools just accept hallucinations as a cost of doing business — LogiCoal uses multiple models to fact-check themselves, because shipping broken code "confidently" isn't acceptable. No CLI tool handles graphic generation well, let alone producing clean SVGs out of the box. I finally got tired of stitching together 2-3 custom integrations just to get basic functionality that should be built in from day one. It's been a lot of work and it's not flawless, but it finally stands up to the major options out there (Claude,Codex,Cursor etc) — without the price tag. LogiCoal is free for life with monthly usage limits. Paid tiers exist, but every tier has the exact same features and capabilities — no gated functionality. My philosophy: build something genuinely useful, and the paid tiers will eventually sustain the servers and dev time. A professional-grade free option has always been the priority. Would love some feedback (positive and/or negative.... Ill read it all).
Ryan Thill

Multi-agent CLI assistants tend to break at scale on unsafe tool execution plus context blowups where “autocompact” drops the one file that matters and hallucinations sneak back in.

Best practice is deterministic repo indexing (tree-sitter + ripgrep), incremental retrieval with stable citations to exact lines, and sandboxed command execution with an allowlist + dry-run diffs before apply.

How are you implementing autocompact (summaries vs selective chunk eviction), and what guarantees do you provide that proposed shell commands and patches are reproducible and safe?