[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
This repository contains a hand-curated resources for Prompt Engineering with a focus on Generative Pre-trained Transformer (GPT), ChatGPT, PaLM etc.
Key parameters and specifications
Key parameters and specifications
Parameter
Value
Language
Python
Category
AI Engineering
Subcategory
Give agent knowledge
Stars
6,558
Forks
821
Contributors
37
Created date
2024-12-24
Updated date
2026-10-15
Stars in 1 day
1
Stars in 7 days
-3
Rank
4,526
Previous rank
18,242
Rank change
13,716
7-day stars rank
18,543
Previous 7-day stars rank
18,640
7-day stars rank change
97
Total stars rank
2,170
Previous total stars rank
2,167
Total stars rank change
-3
Country
USA
README summary
Open-source context retrieval layer for AI agents and RAG systems. Airweave connects to your apps, tools, and databases, continuously syncs their data, and exposes it through a unified, LLM-friendly search interface. AI agents query Airweave to retrieve relevant, grounded, up-to-date context from multiple sources in a single request. Where it fits Airweave sits between your data sources and AI systems as shared retrieval infrastructure. It handles authentication, ingestion, syncing, indexing, and retrieval so you don't have
to rebuild fragile pipelines for every agent or integration. **Connect** your apps, databases, and documents (50+ integrations) 2. **Airweave** syncs, indexes, and exposes your data through a unified retrieval layer 3. **Agents query** Airweave via our SDKs, REST API, MCP, or native integrations with popular agent frameworks 4. **Agents retrieve** relevant, grounded context on demand Quickstart Cloud-hosted: app. Tech Stack **Frontend**: React/TypeScript with ShadCN **Backend**: FastAPI (Python) **Databases**: PostgreSQL (metadata), Vespa (vectors) **Workers**: Temporal (orchestration), Redis (pub/sub
) **Deployment**: Docker Compose (dev), Kubernetes (prod) Contributing We welcome contributions! License MIT License Discord · Issues · Twitter
Frequently asked questions
How many stars and forks are recorded?
airweave-ai/airweave has 6,558 stars and 821 forks.
What is the repository rank?
airweave-ai/airweave is ranked 4,526.
What language and category are recorded?
airweave-ai/airweave has 6,558 stars, uses Python and belongs to AI Engineering.
Which repository is closest in rank?
airweave-ai/airweave is compared with julep-ai/julep, ranked 4,525 with 6,576 stars.
README
Open-source context retrieval layer for AI agents and RAG systems.
What is Airweave?
Airweave connects to your apps, tools, and databases, continuously syncs their data, and exposes it through a unified, LLM-friendly search interface. AI agents query Airweave to retrieve relevant, grounded, up-to-date context from multiple sources in a single request.
Where it fits
Airweave sits between your data sources and AI systems as shared retrieval infrastructure. It handles authentication, ingestion, syncing, indexing, and retrieval so you don't have to rebuild fragile pipelines for every agent or integration.
How it works
Connect your apps, databases, and documents (50+ integrations)
Airweave syncs, indexes, and exposes your data through a unified retrieval layer
Agents query Airweave via our SDKs, REST API, MCP, or native integrations with popular agent frameworks
Agents retrieve relevant, grounded context on demand