DeepTutor vs hermes-agent
hermes-agent is much bigger: 241.7k stars against 38.8k. Over the days we have tracked them DeepTutor moved +58.3% and hermes-agent +11.9%, so DeepTutor 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
A self-hostable, multi-agent tutoring platform with built-in RAG, three-layer persistent memory and a pluginable Skills ecosystem for lifelong personalized learning.
- Stars
- 38.8k
- Tracked growth
- +58.3%
- Maturity
- ●●●●●
- Last commit
- 2d ago
- Language
- Python
- License
- Apache-2.0
- Cost to run
- Free to self-host; uses your model API key or local LLMs
A self-hostable personal agent with a built-in closed learning loop that creates, persists, and self-improves skills from its own experience.
- Stars
- 241.7k
- Tracked growth
- +11.9%
- Maturity
- ●●●●●
- Last commit
- 12m ago
- Language
- Python
- License
- MIT
- Cost to run
- Your API key or Nous Portal subscription
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 | DeepTutor | hermes-agent |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Multi-doc RAG | ●●●●● Related files |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Basic filters | ●●●●● Approval & allowlist |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Plugin & skills | ●●●●● Skills & config |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Fully local | ●●●●● Self-hostable |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● BYOK + local | ●●●●● Bring-your-own-key |
Setup ease What it takes to get a first useful run out of it. | ●●●●● One-command start | ●●●●● One-command install |
Which one to pick
Pick DeepTutor if…
Privacy-first — run locally or with your own API keys while getting a production-grade, extensible tutoring stack (agents, RAG, persistent memory, and Skills marketplace).
Pick hermes-agent if…
Continual learning — pick Hermes when you want a self-hosted, continuously learning personal assistant that builds and improves skills across sessions and integrates with messaging platforms.
What people want from each one
HKUDS/DeepTutor
Hacker News: DeepTutor: Agent-Native Personalized Tutoring drew 2 points and 0 comments.
NousResearch/hermes-agent
Hacker News: Nous Research edits GitHub issue to remove plagiarism claims about Hermes Agent drew 8 points and 1 comments.
Questions people ask
Is DeepTutor better than hermes-agent?
Neither one leads on the six capability axes, so the choice comes down to which of them fits the way you already work. DeepTutor is worth picking when privacy-first — run locally or with your own API keys while getting a production-grade, extensible tutoring stack (agents, RAG, persistent memory, and Skills marketplace).
Which of DeepTutor and hermes-agent keeps my code private?
DeepTutor: Fully local (5/5). hermes-agent: Self-hostable (4/5).
What does each one cost to run?
DeepTutor: Free to self-host; uses your model API key or local LLMs. hermes-agent: Your API key or Nous Portal subscription.
Full profiles: HKUDS/DeepTutor and NousResearch/hermes-agent. Everything else in Personal assistants.