Skip to content

Repository files navigation

local-ai

Two-tier orchestration: proprietary APIs plan and verify; local Ollama models handle small coding task contracts. Data-driven capex decision after 1–2 months of measured MVP.

What this is

  • Orchestrator tier: API (Claude Opus/Sonnet, or alternatives) — decomposes, plans, reviews, merges
  • Worker tier: Local Ollama models — executes small, constrained coding tasks with minimal repo context
  • Goal: Replace 70%+ of API grunt spend with local inference without losing >15% quality
  • Decision gate: 1–2 months of real data → stay / upgrade / hybrid

Install

git clone https://github.com/AdarGit008/local-ai.git
cd local-ai

Structure

Path Purpose
configs/ Worker profile definitions (model, context, task types)
data/ Benchmark results, hardware tests, session summaries
docs/ Project intent, prior orchestration research
mvp/ MVP architecture, task contracts, instrumentation harness
research/ External landscape synthesis, hardware capability assessment

Key findings so far

  • Parallel workers are viable: Ollama runs different models as separate GPU processes; same-model concurrency possible via OLLAMA_NUM_PARALLEL
  • Best 6GB model candidate: GLM-4.7-Flash (30B MoE, 3B active, ~5GB Q4, 59.2% SWE-bench)
  • Industry benchmark: EvalPlus (HumanEval+, MBPP+) gives comparable pass@1 scores

Status

Derived — see docs/start-here.md.

About

Two-tier local/API AI orchestration — data-driven capex decisions

Resources

Security policy

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages