DeepLethe
@deeplethe • AI research and products unbounded by precedent.. Use this route to separate flagship concentration from portfolio breadth before you treat a publisher as broadly strong.
Portfolio concentration
100%
Top three share
Shows whether the organization is driven by one breakout repo or several visible projects.
Breadth
9 repos
Visible snapshot
7 repositories updated in the last 90 days.
Leading language
Python
Portfolio mix
Python (6), Rust (2), Shell (1)
Average size
701
Stars per repository
Useful for distinguishing one flagship-heavy publisher from a repeatable portfolio.
Updated: 2026-08-22(12d ago)GitHub API fallback9 repositories
100%
of the visible star count comes from this organization's top three repositories.
701
stars per repository in this same snapshot.
Python
is the most common language here, with 7 repositories updated in the last 90 days.
Why this rank
This organization stands out because one flagship repo drives 55% of its visible star count.
Flagship share 55%Breakout repo: utopia
Organization pages work best when you separate portfolio breadth from flagship concentration. In DeepLethe's case, the visible top three repositories account for about 100% of total stars in this snapshot, which helps explain whether the organization is known for one breakout project or for a broader repeatable portfolio.
The dominant language mix here is Python (6), Rust (2), Shell (1). That makes this page useful not just for popularity checks, but also for seeing what technical shape an organization's public ecosystem actually has.
Top Repositories
| # | Repository | Language | Stars |
|---|---|---|---|
| 1 | deeplethe/utopia World's first open-source enterprise world model. | Rust | 3.5K |
| 2 | deeplethe/forkd Fork() for AI agent microVMs. Spawn 100 children in ~100ms from a warm parent; BRANCH a live VM in ~150ms. KVM-isolated, snapshot CoW. | Rust | 2.8K |
| 3 | deeplethe/ontology2sql Ontology-grounded agentic Text-to-SQL for BIRD Mini-Dev | Python | 13 |
| 4 | deeplethe/lethe The best-benchmarked open-source AI memory system and the first AI memory built to forget. | Python | 8 |
| 5 | deeplethe/pulse-spatial Modal spatiotemporal semantics for executable knowledge graphs | Python | 2 |
| 6 | deeplethe/demarche Vendor-neutral identity verification for AI agents | Python | 2 |
| 7 | deeplethe/pulse Reference implementation and reproducibility artifact for the PULSE process-aware semantic modeling language | Python | 1 |
| 8 | deeplethe/llm-coupling-gain Measuring when emergent consensus is real in LLM agent societies: the coupling gain (gamma), a backfire coefficient, and a (slope,bias) validity diagnostic. Code + per-run logs. | Python | 0 |
| 9 | deeplethe/forkd-action GitHub Action for forkd microVM sandboxes — spawn sandboxes, run commands, BRANCH from CI | Shell | 0 |
Next step after the organization read
Open a flagship repository, compare a couple of portfolio leaders, or return to the organization map when you want a broader concentration read.
Learn and methodology
Keep trust-building context reachable, but behind the first data read instead of ahead of it.
How to read this organization snapshot
Total stars are useful as a discovery signal, but they do not tell you whether a team maintains every repository equally. Pair this page with release cadence, maintainer activity, and the flagship concentration shown above before making adoption decisions.
For broader background on GitStar's ranking logic and editorial guidance, see Methodology & Editorial Standards.