Sandbox Charts
Discover tools and use the data to compare them.
Dated, sourced editions
Update overdue. The latest published edition remains available.
GITHUB TOP 20
Explore open-source projects in the GitHub ranking.
Understand this edition's data
This edition ranks cumulative stars. The available history was not yet sufficient to measure seven-day growth.
- Latest included observation
- Frozen calculation
- Publication
Calculation version : github-momentum-v1+stars
20 entries shown in GITHUB TOP 20.
01-
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
100,0/100SANDBOX SCORE-Introduction
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
Data
SANDBOX score: 100,0 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#11 editions in the Top 20 · best rank #1
Measurements, score components and sources
Score components
- reach
- 100,0/100
- GitHub popularity
- 100,0/100
02-
anything-llm
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
98,8/100SANDBOX SCORE-Introduction
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
Data
SANDBOX score: 98,8 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#21 editions in the Top 20 · best rank #2
Measurements, score components and sources
Score components
- reach
- 98,8/100
- GitHub popularity
- 98,8/100
03-
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
97,6/100SANDBOX SCORE-Introduction
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Data
SANDBOX score: 97,6 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#31 editions in the Top 20 · best rank #3
Measurements, score components and sources
Score components
- reach
- 97,6/100
- GitHub popularity
- 97,6/100
04-
openhuman
The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.
96,4/100SANDBOX SCORE-Introduction
The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.
Data
SANDBOX score: 96,4 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#41 editions in the Top 20 · best rank #4
Measurements, score components and sources
Score components
- reach
- 96,4/100
- GitHub popularity
- 96,4/100
05-
Codewhale
Open-source Rust agent engine and terminal client for Codewhale, with provider choice, tools, approvals and receipts.
95,2/100SANDBOX SCORE-Introduction
Open-source Rust agent engine and terminal client for Codewhale, with provider choice, tools, approvals and receipts.
Data
SANDBOX score: 95,2 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#51 editions in the Top 20 · best rank #5
Measurements, score components and sources
Score components
- reach
- 95,2/100
- GitHub popularity
- 95,2/100
06-
quivr
An open-source engine that turns continuous content streams into search and monitoring. Durable ingestion, hybrid search, alerts, and plugins for formats, models and business rules.
94,0/100SANDBOX SCORE-Introduction
An open-source engine that turns continuous content streams into search and monitoring. Durable ingestion, hybrid search, alerts, and plugins for formats, models and business rules.
Data
SANDBOX score: 94,0 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#61 editions in the Top 20 · best rank #6
Measurements, score components and sources
Score components
- reach
- 94,0/100
- GitHub popularity
- 94,0/100
07-
DeepSeek-Reasonix
A reliable coding agent for complex software engineering tasks.
92,9/100SANDBOX SCORE-Introduction
A reliable coding agent for complex software engineering tasks.
Data
SANDBOX score: 92,9 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#71 editions in the Top 20 · best rank #7
Measurements, score components and sources
Score components
- reach
- 92,9/100
- GitHub popularity
- 92,9/100
08-
cognee
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
91,7/100SANDBOX SCORE-Introduction
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
Data
SANDBOX score: 91,7 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#81 editions in the Top 20 · best rank #8
Measurements, score components and sources
Score components
- reach
- 91,7/100
- GitHub popularity
- 91,7/100
09-
Scrapegraph-ai
Python scraper based on AI
90,5/100SANDBOX SCORE-Introduction
Python scraper based on AI
Data
SANDBOX score: 90,5 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#91 editions in the Top 20 · best rank #9
Measurements, score components and sources
Score components
- reach
- 90,5/100
- GitHub popularity
- 90,5/100
10-
composio
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
89,3/100SANDBOX SCORE-Introduction
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
Data
SANDBOX score: 89,3 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#101 editions in the Top 20 · best rank #10
Measurements, score components and sources
Score components
- reach
- 89,3/100
- GitHub popularity
- 89,3/100
11-
mastra
Mastra is the modern TypeScript framework for AI-powered applications and agents.
88,1/100SANDBOX SCORE-Introduction
Mastra is the modern TypeScript framework for AI-powered applications and agents.
Data
SANDBOX score: 88,1 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#111 editions in the Top 20 · best rank #11
Measurements, score components and sources
Score components
- reach
- 88,1/100
- GitHub popularity
- 88,1/100
12-
jcode
High performance coding agent harness written in rust
86,9/100SANDBOX SCORE-Introduction
High performance coding agent harness written in rust
Data
SANDBOX score: 86,9 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#121 editions in the Top 20 · best rank #12
Measurements, score components and sources
Score components
- reach
- 86,9/100
- GitHub popularity
- 86,9/100
13-
eliza
Open source agentic operating system
85,7/100SANDBOX SCORE-Introduction
Open source agentic operating system
Data
SANDBOX score: 85,7 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#131 editions in the Top 20 · best rank #13
Measurements, score components and sources
Score components
- reach
- 85,7/100
- GitHub popularity
- 85,7/100
14-
txtai
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
84,5/100SANDBOX SCORE-Introduction
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
Data
SANDBOX score: 84,5 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#141 editions in the Top 20 · best rank #14
Measurements, score components and sources
Score components
- reach
- 84,5/100
- GitHub popularity
- 84,5/100
15-
OpenCreator
Formerly KrillinAI, VideoTranslation and Dubbing Tool. Open-source AI workspace for creators, powered by Codex. Video downloading, video translation, create videos, images, voice, avatars, and edits with Agents in one place. Suitable for your Social Media like YouTube, TikTok, Instagram, etc.
83,3/100SANDBOX SCORE-Introduction
Formerly KrillinAI, VideoTranslation and Dubbing Tool. Open-source AI workspace for creators, powered by Codex. Video downloading, video translation, create videos, images, voice, avatars, and edits with Agents in one place. Suitable for your Social Media like YouTube, TikTok, Instagram, etc.
Data
SANDBOX score: 83,3 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#151 editions in the Top 20 · best rank #15
Measurements, score components and sources
Score components
- reach
- 83,3/100
- GitHub popularity
- 83,3/100
16-
LMCache
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
82,1/100SANDBOX SCORE-Introduction
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
Data
SANDBOX score: 82,1 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#161 editions in the Top 20 · best rank #16
Measurements, score components and sources
Score components
- reach
- 82,1/100
- GitHub popularity
- 82,1/100
17-
openchamber
Agentic Development Environment based on OpenCode AI agent
81,0/100SANDBOX SCORE-Introduction
Agentic Development Environment based on OpenCode AI agent
Data
SANDBOX score: 81,0 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#171 editions in the Top 20 · best rank #17
Measurements, score components and sources
Score components
- reach
- 81,0/100
- GitHub popularity
- 81,0/100
18-
ekko-studio
Ekko Studio is a local-first AI workspace for multi-agent chat, coding, and visual workflows, available on desktop and the web.
79,8/100SANDBOX SCORE-Introduction
Ekko Studio is a local-first AI workspace for multi-agent chat, coding, and visual workflows, available on desktop and the web.
Data
SANDBOX score: 79,8 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#181 editions in the Top 20 · best rank #18
Measurements, score components and sources
Score components
- reach
- 79,8/100
- GitHub popularity
- 79,8/100
19-
rig
⚙️🦀 Build modular and scalable LLM Applications in Rust
78,6/100SANDBOX SCORE-Introduction
⚙️🦀 Build modular and scalable LLM Applications in Rust
Data
SANDBOX score: 78,6 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#191 editions in the Top 20 · best rank #19
Measurements, score components and sources
Score components
- reach
- 78,6/100
- GitHub popularity
- 78,6/100
20-
harness-sdk
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
77,4/100SANDBOX SCORE-Introduction
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
Data
SANDBOX score: 77,4 out of 100.
30 DAYS MOMENTUM
History is being collected10.10#201 editions in the Top 20 · best rank #20
Measurements, score components and sources
Score components
- reach
- 77,4/100
- GitHub popularity
- 77,4/100
