Mintplex-Labs/anything-llm

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 52 minutes ago
Added to GitGenius on April 7th, 2024
Created on June 4th, 2023
Open Issues & Pull Requests: 327 (+0)
Number of forks: 7,171
Total Stargazers: 65,132 (+3)
Total Subscribers: 410 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 7.7 hours
Mean response time: 15.0 days
90th percentile: 11.3 days
Tracked items: 3,119

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 94% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "core-team-only" is answered fastest, typically in about an hour, while "Integration Request" waits about 2 days. 47% of tracked open issues have had no activity in three months. Only 11% of issues opened in the past year have been closed.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 318
New in 7 days: 18
Closed in 7 days: 17
Avg open age: 252 days
Stale 30+ days: 281
Stale 90+ days: 217

Recent activity

Opened in 7 days: 16
Closed in 7 days: 17
Comments in 7 days: 14
Events in 7 days: 40

Top labels

  • enhancement (1,401)
  • possible bug (1,380)
  • feature request (1,335)
  • needs info / can't replicate (213)
  • investigating (209)
  • Integration Request (163)
  • core-team-only (160)
  • UI/UX (136)

Detailed Description

AnythingLLM is a comprehensive, local-first AI application built in JavaScript that enables users to create a fully-featured private ChatGPT alternative without relying on external services. The project positions itself as an all-in-one solution for document-based chat, AI agent automation, and complex workflow orchestration, with the core philosophy of allowing users to own their intelligence rather than renting it from cloud providers.

AnythingLLM's feature set extends beyond basic chat functionality to include dynamic model routing that automatically directs conversations to optimal providers based on defined rules, automatic and user-managed memory systems, scheduled task execution with cron scheduling, and intelligent skill selection that can reduce token usage by up to 80 percent per query. The platform includes a no-code AI agent builder, Model Context Protocol compatibility, and multi-modal support for both closed and open-source language models. Multi-user instance support with granular permissioning is available in the Docker version, alongside web browsing agents, custom embeddable chat widgets, and a full developer API.

The platform's integration ecosystem is extensive, supporting numerous large language model providers including OpenAI, Anthropic, AWS Bedrock, Google Gemini, Ollama, LM Studio, LocalAI, Together AI, Groq, Mistral, and many others. For embeddings, it offers native AnythingLLM embedders alongside OpenAI, Azure OpenAI, Gemini, and various open-source alternatives. Vector database support includes LanceDB as the default option plus Pinecone, Chroma, Weaviate, Qdrant, Milvus, and others. The application handles document ingestion across multiple formats including PDF, TXT, and DOCX with built-in optimizations for large document sets.

The project's contributor network overlaps with major repositories including Microsoft's VSCode and TypeScript implementations as well as the Rust language repository, suggesting influence from and alignment with significant open-source ecosystems. The application is available as a desktop client for Mac, Windows, and Linux, with a hosted instance option, and operates under the MIT license with active community support through Discord channels.