Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Stop Claude Code from forgetting everything

Details

External ID
46426624
Source
HN
Company
—
Product
Stop Claude Code from forgetting everything
Website domain
github.com
Launched
Dec. 29, 2025
Cohort
—
Upvotes
202
Upvotes percentile
0.9541984732824428
Tags
—
Fetched at
Sept. 7, 2026, 9:25 p.m.
Updated at
Sept. 7, 2026, 9:25 p.m.

Description

I got tired of Claude Code forgetting all my context every time I open a new session: set-up decisions, how I like my margins, decision history. etc.We built a shared memory layer you can drop in as a Claude Code Skill. It’s basically a tiny memory DB with recall that remembers your sessions. Not magic. Not AGI. Just state.Install in Claude Code: /plugin marketplace add https://github.com/mutable-state-inc/ensue-skill /plugin install ensue-memory # restart Claude Code What it does: (1) persists context between sessions (2) semantic & temportal search (not just string grep). Basically git for your Claude brainWhat it doesn’t do: - it won’t read your mind - it’s alpha; it might break if you throw a couch at itRepo: https://github.com/mutable-state-inc/ensue-skillIf you try it and it sucks, tell me why so I can fix it. Don't be kind, tia

Enrichment

Theme
utilities for Claude and Claude Code
Vertical
Horizontal
Function
Dev tools
Audience
Developer
AI stance
AI feature
Project type
Hobby / open-source project
Normalized one-liner
context persistence for claude code
Manually corrected
False

Could you build this?

Yes It is a Claude Code Skill (MCP tool/extension) backed by a local SQLite or vector store database that persists session context and preferences across CLI runs.

Discussion

20 comments analyzed.

Competitors mentioned: Claude.md approaches with markdown guides, Multi-AI consensus (Claude, GPT, Gemini, Grok), Beads project management tool

Concerns raised: Token inefficiency with full LLM round trips vs direct script execution, Skills are functionally equivalent to wrapping prompts - no fundamental difference, Context decay and agent forgetting after context compaction, Agent may not discover or pick up skills reliably, Unclear if smaller targeted Claude.md actually makes meaningful difference

Feature requests: Benchmarks comparing token usage and quality (e.g., Twitter rebuild test across agents), Better context curation metrics proving value vs constant rediscovery, Solution for systematic skill discovery and routing by agents

Competitors

Other products that read as similar to this one — 317 launches clear the similarity bar, closest 8 shown.

Attention rank: #19 of 318 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 53 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a dev tools tool for Sales yet.