claude-mem vs hindsight
claude-mem is much bigger: 94.7k stars against 30.5k. Over the days we have tracked them claude-mem moved +8.2% and hindsight +72.7%, so hindsight is growing faster right now.
Neither one leads on the six capability axes, so the choice comes down to which of them fits the way you already work.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
Claude-Mem pairs a Claude Code–focused persistent memory with progressive-disclosure search tools and a local worker/web UI to deliver token-efficient, session-persistent context.
- Stars
- 94.7k
- Tracked growth
- +8.2%
- Maturity
- ●●●●●
- Last commit
- 4h ago
- Language
- TypeScript
- License
- Apache-2.0
- Cost to run
- Your API key for model calls; optional cloud backup to cmem.ai
Hindsight provides a learning-focused agent memory with biomimetic data structures and a reflect operation to build mental models, going beyond simple RAG-style recall.
- Stars
- 30.5k
- Tracked growth
- +72.7%
- Maturity
- ●●●●●
- Last commit
- 14h ago
- Language
- Python
- License
- MIT
- Cost to run
- Your LLM API key (or self-hosted models); Hindsight itself can be self-hosted
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | claude-mem | hindsight |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Related files & memory | ●●●●● Related context |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Configurable filters | ●●●●● Rerank & filtering |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Config file & modes | ●●●●● Config API & metadata |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Self-hostable (local worker) | ●●●●● Self-hostable |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Bring-your-key (many providers) | ●●●●● Bring-your-own / local |
Setup ease What it takes to get a first useful run out of it. | ●●●●● One-command install | ●●●●● One-command start |
Which one to pick
Pick claude-mem if…
Easy setup — one-command installer and a local worker that preserves and injects compressed session context into future Claude Code sessions.
Pick hindsight if…
Learning-focused — choose Hindsight when you need agents that form and reflect on long-term memories (mental models) with easy self-hosted deployment and multi-provider model support.
What people want from each one
thedotmack/claude-mem
Hacker News: Claude-Mem drew 2 points and 1 comments.
- [plan-14] Child Process Ownership — every process the worker spawns dies with the worker 👍 2
- SyncHub projector stalled: projected_seq stays "0" while head_seq reaches "40", so no push can ever validate 👍 2
- Cloud sync permanently stuck: SyncHub push response violates head_seq <= projected_seq invariant 👍 2
vectorize-io/hindsight
- Feature Request: Team, agent, and memory-level access control 👍 5
- reranker(typesafe): every recall fails over on banks with realistic-size memories — the request ships full candidate text against Jev's ~32k budget, and nothing bounds it 👍 2
- [Feature]: I'd like to benefit from disk savings with Embedding Quantization 👍 1
Questions people ask
Is claude-mem better than hindsight?
Neither one leads on the six capability axes, so the choice comes down to which of them fits the way you already work. claude-mem is worth picking when easy setup — one-command installer and a local worker that preserves and injects compressed session context into future Claude Code sessions.
Which of claude-mem and hindsight keeps my code private?
claude-mem: Self-hostable (local worker) (4/5). hindsight: Self-hostable (4/5).
What does each one cost to run?
claude-mem: Your API key for model calls; optional cloud backup to cmem.ai. hindsight: Your LLM API key (or self-hosted models); Hindsight itself can be self-hosted.
Full profiles: thedotmack/claude-mem and vectorize-io/hindsight. Everything else in Memory & context.