Jordan-Hall / Jordan-Hall/browser
EPIC: Built-in local intelligence
- Dominant language
- No language data
- Stars
- 0
- Forks
- 0
- PR merge metrics
- No merged PRs in 30d
Description
Programme: #1
Own local inference runtime abstraction, model packs, hardware-aware routing and the built-in local coding/planning agent. Local capability is a measured product guarantee, not a model-name checkbox.
## Child issues
- [ ] #61 LOCAL-01 — Offline/local/hybrid inference policies
- [ ] #62 LOCAL-02 — Role-specific model packs
- [ ] #63 LOCAL-03 — Native local coding and tool agent
- [ ] #64 LOCAL-04 — Hardware/resource profiling and optimization
## Cross-cutting gates
Offline/local/hybrid modes are explicit, no hidden cloud fallback, model packages are signed/licensed/tested, resource scheduling preserves UI/speech responsiveness, and coding quality is measured by verified outcomes.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with child issues #61–#64 to understand the planned work: inference policies, model packs, a local coding and tool agent, and hardware/resource profiling. Completion is defined by the cross-cutting gates: explicit offline/local/hybrid modes without hidden cloud fallback, signed/licensed/tested model packages, responsive resource scheduling, and measured verified coding outcomes.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai, infrastructure, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100