datalab-to/chandra
Chandra is an OCR model converting images and PDFs into structured HTML, Markdown, or JSON.
As of Oct 30, 2026, datalab-to/chandra has 12,641 GitHub stars, +93 since Oct 23, 2026, #88 among Model & inference repos this week.
- Total stars
- 12,641
- Last day
- +11
- Since Oct 23, 2026
- +93
- Weekly rank
- #552
- Category
- Model & inference repos
- Language
- Python
Stars gained per day
Oct 23, 2026 – Oct 29, 2026 · peak +29/day
Links
chandra alternatives in Model & inference repos
- Niko1221/Strata · 36,213 ★ · +5,414 /7dStrata is a local inference engine running Qwen3.8-Flash-Next on consumer hardware.
- tashfeenahmed/freellmapi · 44,241 ★ · +4,475 /7dAggregates free tiers from 34 LLM providers into one OpenAI-compatible endpoint with routing and failover.
- Fractal-Compute-Orchestrations/FractalWorkspace · 7,876 ★ · +4,130 /7dA distributed framework for federated learning and edge model training across Android and Python nodes.
- deepseek-ai/DeepInfer · 24,385 ★ · +4,004 /7dOpen-source offline inference framework for DeepSeek models with optimized kernels, parallelism, and scheduling.
- rohitg00/ai-engineering-from-scratch · 75,642 ★ · +3,062 /7dOpen-source AI engineering curriculum with 542 lessons covering model internals, retrieval, and agent runtimes.
- cheaper-inference/OmniRoute · 82,667 ★ · +2,648 /7dOpen-source MIT AI gateway routing one endpoint to 375 providers and 1,400+ models.
- Alishahryar1/free-claude-code · 65,028 ★ · +2,306 /7dA proxy that routes Claude Code and other coding agents to 61 free and paid model providers.
- Edge0-AI/Edge0 · 8,772 ★ · +2,205 /7dStreams MoE weights from SSD so 35B models run in about 2.5 GB of RAM.
Badge for your README
Data: daily star-total snapshots from the GitHub GraphQL API; stars gained = difference between snapshots. GitHub search and GH Archive are used to find repos. Updated daily around 02:30 UTC, counting through the last complete UTC day. · By Kai
How we rank · Weekly archive · RSS · JSON API