LocalGPT
A local-first AI assistant in Rust with persistent memory
Details
- External ID
- 46930391
- Source
- HN
- Company
- —
- Product
- LocalGPT
- Website domain
- github.com
- Launched
- Feb. 8, 2026
- Cohort
- —
- Upvotes
- 331
- Upvotes percentile
- 0.9838274932614556
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
I built LocalGPT over 4 nights as a Rust reimagining of the OpenClaw assistant pattern (markdown-based persistent memory, autonomous heartbeat tasks, skills system).It compiles to a single ~27MB binary — no Node.js, Docker, or Python required.Key features:- Persistent memory via markdown files (MEMORY, HEARTBEAT, SOUL markdown files) — compatible with OpenClaw's format - Full-text search (SQLite FTS5) + semantic search (local embeddings, no API key needed) - Autonomous heartbeat runner that checks tasks on a configurable interval - CLI + web interface + desktop GUI - Multi-provider: Anthropic, OpenAI, Ollama etc - Apache 2.0Install: `cargo install localgpt`I use it daily as a knowledge accumulator, research assistant, and autonomous task runner for my side projects. The memory compounds — every session makes the next one better.GitHub: https://github.com/localgpt-app/localgpt Website: https://localgpt.appWould love feedback on the architecture or feature ideas.
Enrichment
- Theme
- lightweight and on-device AI runtimes
- Vertical
- Horizontal
- Function
- Agent / copilot
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- local ai assistant with memory for developers
- Manually corrected
- False
Could you build this?
Yes The project is a straightforward local AI CLI agent written in Rust using local markdown files for memory and calling standard LLM APIs.
Discussion
20 comments analyzed.
Competitors mentioned: Ollama, vLLM, OpenRouter, LocalGPT, Gwen3 Coder Next
Concerns raised: Information sharing capability when multiple users have access, Misleading name - relies on external LLM providers, not truly local, Agent functionality not working properly, High electricity costs scaling with parameter count, Local models insufficient speed and accuracy on 16GB RAM
Feature requests: Model fallback support, Comprehensive data flow tracking and policies, Policy controls like blocking secrets over email, Local LLM bundled by default, Rename to more accurately reflect local vs external LLM usage
Competitors
Other products that read as similar to this one — 106 launches clear the similarity bar, closest 8 shown.
Attention rank: #5 of 107 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 97 days after the earliest competitor.
- Clawbernetes · hn · 2026-02-20 · 5 upvotes · similarity 0.45
- Moltis · hn · 2026-02-12 · 131 upvotes · similarity 0.43
- Build apps with 500 models locally. No tracking, no cloud, just code · hn · 2025-12-21 · 6 upvotes · similarity 0.41
- Hibana · hn · 2026-02-06 · 18 upvotes · similarity 0.40
- I made an open-source Rust program for memory-efficient genomics · hn · 2025-11-13 · 17 upvotes · similarity 0.38
- Artifact Keeper · hn · 2026-02-06 · 166 upvotes · similarity 0.38
- I embedded 685M public texts in 32 minutes (on 8x A100, Rust, TensorRT) · hn · 2026-06-04 · 7 upvotes · similarity 0.38
- Bloodhound · hn · 2025-12-09 · 5 upvotes · similarity 0.37
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.