A
local-deep-research
83.3
9,596 stars · MIT
Self-Hosted
unsloth leads by 14.6 · clear
A
83.3
9,596 stars · MIT
B · leads
97.9
79,671 stars · Apache-2.0
local-deep-research versus unsloth is a Self-Hosted comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. Both projects are written mainly in Python. The composite score is 83.3 for local-deep-research and 97.9 for unsloth.
unsloth has 79,671 GitHub stars to local-deep-research's 9,596, a gap of 70,075 (8.30×). Forks are 929 for local-deep-research and 7,439 for unsloth. On the log scale used inside this pair, adoption is 81 versus 100, and the fork community is 77 versus 100.
Push history: local-deep-research was last pushed on 17 November 2026 (0 days ago), and unsloth was last pushed on 17 November 2026 (0 days ago). Open issues stand at 1,481 for local-deep-research (0.154 per star) and 469 for unsloth (0.006 per star). Issue-health scores are 34 and 84; activity scores are 100 and 100.
local-deep-research is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. unsloth is listed as Apache-2.0, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. License scores in this pair are 96 for local-deep-research and 96 for unsloth. This is a procurement signal, not legal advice.
In Self-Hosted, both local-deep-research (9,596 stars) and unsloth (79,671 stars) are marked self-hostable. Deploy scores are 100 and 100. Running either one means you own upgrades, backups, and the license duties that follow a modified copy. Pricing labels on file: local-deep-research is open source, unsloth is open source.
unsloth is ahead on every scored dimension that is not level. Level dimensions: recent activity, license flexibility, self-hosting. The widest gap is issue health at 50 points (34 vs 84), and the tightest is self-hosting at 0 points (100 vs 100).
unsloth finishes ahead at 97.9 against local-deep-research at 83.3, a 14.6 point clear margin under the published weights.
Scores are computed inside this pair only. Method and weights.
Bars are scaled within the row. Higher is stronger. Open issues are a raw count, so that row has no bar.
| Signal | local-deep-research | unsloth |
|---|---|---|
| GitHub stars | 9,596 | 79,671 |
| Forks | 929 | 7,439 |
| Open issues | 1,481 | 469 |
| Adoption | 81 | 100 |
| Activity | 100 | 100 |
| Community | 77 | 100 |
| Issue health | 34 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 83.3 | 97.9 |
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
unsloth has more GitHub stars: 79,671 versus 9,596 for local-deep-research. The gap is 70,075 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both local-deep-research and unsloth as self-hostable. Confirm each project's deploy docs before you plan a migration.
local-deep-research is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. unsloth is listed as Apache-2.0, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
unsloth scores 97.9 and local-deep-research scores 83.3. This page calls that a clear lead for unsloth.