Shodh– AI memory that learns from use, no LLM calls, single Rust binary
Details
- External ID
- 47197382
- Source
- HN
- Company
- —
- Product
- Shodh– AI memory that learns from use, no LLM calls, single Rust binary
- Website domain
- github.com
- Launched
- Feb. 28, 2026
- Cohort
- —
- Upvotes
- 6
- Upvotes percentile
- 0.28099730458221023
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Enrichment
- Theme
- ML inference and model optimization
- Vertical
- Horizontal
- Function
- Model & infra
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- in-process ai memory system without external api calls
- Manually corrected
- False
Could you build this?
No Implementing local associative memory and continuous learning in a standalone binary without LLMs requires specialized machine learning and systems research (e.g., local vector quantization, graph networks, or biologically inspired algorithms).
What it would actually take: This requires a low-footprint Rust architecture implementing on-device incremental learning, such as hyperdimensional computing, online vector embeddings, or Hebbian associative memory graphs without external model dependencies. The hard parts are memory retention without catastrophic forgetting, fast similarity retrieval in fixed memory, and cross-platform native compilation. It requires expertise in non-standard AI/cognitive architectures and embedded systems engineering.
Discussion
1 comment analyzed.
Competitors mentioned: mem0, Cognee, Zep
Concerns raised: No formal retrieval quality benchmarks, ~400ms warm latency for full context pipeline, Solo project
Competitors
Other products that read as similar to this one — 1713 launches clear the similarity bar, closest 8 shown.
Attention rank: #1196 of 1714 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 122 days after the earliest competitor.
- Mnemo · hn · 2026-06-03 · 60 upvotes · similarity 0.73
- Hebbs · hn · 2026-03-09 · 6 upvotes · similarity 0.69
- Lossless-memory · hn · 2026-09-21 · 67 upvotes · similarity 0.68
- DecisionNode · hn · 2026-04-10 · 23 upvotes · similarity 0.65
- Jev-Mem · github · 2026-09-20 · 72 upvotes · similarity 0.65
- retain-ai · github · 2026-09-11 · 8 upvotes · similarity 0.64
- MemoryOps · hn · 2026-06-22 · 5 upvotes · similarity 0.64
- Memctl v0.1.0 Open source shared persistent memory for AI coding agents · hn · 2026-03-01 · 7 upvotes · similarity 0.64
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a model & infra tool for Fintech yet.