Show HN: Eigin. Local-first and no-shell personal AI for iOS
Hey HN, we're Daniel and Therkel and we're working on Eigin, a personal agent built to be private, safe and under your control. What makes Eigin different from the mainstream personal agents is it's local-first architecture (chats, memory, agent runtime on your device), closed-set tool model (fixed set of tools, permissions in execution path) and it being open source under AGPL. Personal agents are exciting as an emerging category. We believe that technology this personal should belong to the pe
Read original source
Source record
Recorded metrics
points · 2 votes
2026-11-10 21:00:27.077Z
cumulative since publication
Research analysis
Project record
Repository: Eigin-AI/Eigin. Source account: Hey HN, we're Daniel and Therkel and we're working on Eigin, a personal agent built to be private, safe and under your control. What makes Eigin different from the mainstream personal agents is it's local-first architecture (chats, memory, agent runtime on your device), closed-set tool model (fixed set of tools, permissions in execution path) and it being open source under AGPL. Personal agents are exciting as an emerging category. We believe that technology this personal should belong to the pe
Observed adoption & comparisons
Source votes: 2 votes (Nov 10, 2026 UTC; cumulative since publication); previous same-scope observation: 2 (Nov 10, 2026 UTC). These observations do not establish demand growth. Recent records to compare: “addyosmani/agent-skills” (GitHub Trending, Nov 10, 2026); “anthropics/skills” (GitHub Trending, Nov 10, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.
Adoption decision
Evaluate it against the tool or manual workflow it would replace. The stored record supports discovery; it does not yet establish reliability, lower operating cost or commercial adoption.
Unverified requirements
Not verified: license permissions, required hardware, installation steps, maintenance status and a representative task with its failure cases.
Next test
Choose one real task and a current alternative. Record the commit, environment, input, output, elapsed time and failure behavior; retain the result before recommending adoption.