Repositories
8
Net stars gained, last 7 days
+623
Top-level Tag
Net stars gained each day, last 90 days
Peak days
- 1
Sep 18, 2026 +425 net stars (median day +69)
- vercel-labs/json-render+392 (92%)
Published v0.21.0 on Sep 18, 2026
- pydantic/pydantic-ai+16 (4%)
- google/langextract+7 (2%)
- 2
Sep 20, 2026 +726 net stars (median day +69)
- vercel-labs/json-render+674 (93%)
- pydantic/pydantic-ai+19 (3%)
- dottxt-ai/outlines+12 (2%)
- 3
Sep 21, 2026 +486 net stars (median day +69)
- vercel-labs/json-render+409 (84%)
- pydantic/pydantic-ai+32 (7%)
- dottxt-ai/outlines+13 (3%)
- 4
Sep 23, 2026 +360 net stars (median day +69)
- nokia-applied-research/AnyJev+240 (67%)
Created on Sep 21, 2026
- vercel-labs/json-render+87 (24%)
- google/langextract+13 (4%)
- 5
Sep 25, 2026 +381 net stars (median day +69)
- nokia-applied-research/AnyJev+215 (56%)
Created on Sep 21, 2026
- google/langextract+104 (27%)
- vercel-labs/json-render+35 (9%)
A peak day has at least 2 times the net stars of the median day of this chart, and at least 100 more. For each peak day, the list shows the repositories that gained the most net stars that day. It also shows their GitHub releases of that day or the day before (UTC), and their creation date when it was 14 days or less before. These events occur near the same day. They do not show why the stars came.
Largest
Most stars in total now.
readme:
Enforces a consistent output schema based on your few-shot examples, leveraging controlled generation in supported models like Gemini to guarantee robust, structured results.
readme:
A JSON schema is actually a context free grammar, and hence it can be used to constrain an LLM using Guidance.
readme:
Give the agent an output type and tools, and every run comes back validated and typed:
readme:
AI generates interfaces from natural language prompts, constrained to components you define.
readme:
Outlines guarantees structured outputs during generation — directly from any LLM.
readme:
Instructor provides automatic validation, retries, streaming, and nested object support.
description:
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training.
readme:
Replies are written in each model's own tool-call format under a grammar applied on the GPU
Newest Admissions
Entered the index by the rising rule, newest first.
readme:
Replies are written in each model's own tool-call format under a grammar applied on the GPU
description:
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training.
How a repository gets this Tag
An agent reads the description, the GitHub topics, and the start of the README of each repository. It chooses Tags only from the Tag list in the AwesomeRepos source code. For each Tag, it quotes the text. A code check keeps the Tag only when the quote is in that text. The quote under each repository is that evidence. A Tag does not rank repositories. It does not say that one repository can replace another. To report a wrong Tag, use "Report a problem with this page" on the page of the repository. All numbers on this page count only visible repositories.