GitHub topics

llms

17% of these repos are in LLM Infrastructure, 13% in AI Agents and Coding Assistants.

Repositories

23

Total stars

82,450

Trending

lance-format

Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with more integrations coming..

Created Jul 2022

apache-arrow computer-vision data-analysis data-analytics data-centric
Total7,371
30 days +196
ojuschugh1

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.

Created Apr 2026

Total680
30 days +31
katanemo

Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.

Created Jul 2024

ai-gateway ai-gateway-support envoy envoyproxy gateway
Total7,119
30 days +31

Top

lance-format

Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with more integrations coming..

Created Jul 2022

apache-arrow computer-vision data-analysis data-analytics data-centric
Total7,371
katanemo

Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.

Created Jul 2024

ai-gateway ai-gateway-support envoy envoyproxy gateway
Total7,119
RunanywhereAI

Get up and running with GLM-5.3-flash, DeepSeek, Gemma and other open source frontier models.

Created Mar 2026

deepseek frontier-ai glm-5-3 llms local-ai-infrastructure
Total1,571
ojuschugh1

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.

Created Apr 2026

Total680
wisent-ai

Created Mar 2025

activation-steering ai explainability interpretability llms
Total346
oramasearch

OramaCore is the complete runtime you need for your projects, answer engines, copilots, and search. It includes a fully-fledged full-text search engine, vector database, LLM interface, and many more utilities.

Created Oct 2024

Total266
nooscraft

CLI tool – estimates LLM tokens/costs and runs provider-aware load tests for OpenAI, Anthropic, OpenRouter, or custom endpoints.

Created Nov 2025

llms prompt-engineering rust tokenizer
Total146
t8

Local-first permanent, persistent memory for all agents and humans

Created Mar 2026

agents context-window llms
Total112
eth-sri

Constrained Decoding of Diffusion LLMs with Context-Free Grammars.

Created Aug 2025

constrained-decoding diffusion diffusion-model fill-in-the-middle llm
Total61

Related

All topics →