← Open Source
RedPlanetHQ

core

Your Personal AI OS.

AI EngineeringGive agent knowledgeTypeScript
Open on GitHub
Momentum
+0stars in 24 hours0.0%
2.00k
Stars
195
Forks
+8
This week
20
Contributors
Created 2025-05-27 · Updated 2026-10-15 · #9122 today
Top developers

RedPlanetHQ/core is ranked 9,122 with 1,998 stars.

Same-category comparison

RedPlanetHQ/core is ranked 9,122 among these 8 peers; patterns-ai-core/langchainrb is ranked 9,116.

Same-category comparison
NameRankMetrics
64bit/async-openai9,095
Language:
Rust
Stars:
2,017
Forks:
405
Description:
Rust library for OpenAI.
HKUDS/MiniRAG9,096
Language:
Python
Stars:
2,017
Forks:
257
Description:
[ACL2026] "MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models".
open-compress/claw-compactor9,114
Language:
Python
Stars:
2,003
Forks:
184
patterns-ai-core/langchainrb9,116
Language:
Ruby
Stars:
2,001
Forks:
268
Description:
Build LLM-powered applications in Ruby.
glebkudr/shotgun_code9,128
Language:
Go
Stars:
1,995
Forks:
229
Description:
One‑click codebase “blast” for Large‑Language‑Model workflows.
forloopcodes/contextplus9,149
Language:
TypeScript
Stars:
1,983
Forks:
171
Description:
Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining RAG, Tree-sitter AST, Spectral Clustering, and Obsidian-style linking, Context+ turns a massive codebase into a searchable, hierarchical feature graph.
ICT-BDA/EasyML9,155
Language:
Java
Stars:
1,979
Forks:
433
Description:
Easy Machine Learning is a general-purpose dataflow-based system for easing the process of applying machine learning algorithms to real world tasks.
kajisho5/ffmpeg-skill9,170
Language:
Python
Stars:
1,974
Forks:
162
Description:
Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguageTypeScript
CategoryAI Engineering
SubcategoryGive agent knowledge
KeywordsMCP
Stars1,998
Forks195
Contributors20
Created date2025-05-27
Updated date2026-10-15
Stars in 1 day0
Stars in 7 days8
Rank9,122
Previous rank3,094
Rank change-6,028
7-day stars rank4,443
Previous 7-day stars rank4,189
7-day stars rank change-254
Total stars rank6,351
Previous total stars rank6,345
Total stars rank change-6
README summary

Your Personal AI OS Not a chatbot you open. An AI that is always on, always watching. Open source, self-hosted, yours forever. Tasks Every unit of work is a task with your spec, CORE's plan, live state, and a dedicated chat thread. Each task can spawn a coding session, drive the browser, or run terminal commands. Write and CORE picks it up within 3 minutes, loads context from your repo and memory, and drafts a plan. Voice Press Ctrl

+Option on Mac and speak. Messaging Reach CORE from WhatsApp, Slack, or Telegram. Coding agents CORE spins up Claude Code or Codex sessions with the full task context, runs them on your machine or in Docker/Railway, and opens a PR when done. Sessions keep running when your laptop is closed. Browser A built-in browser CORE can drive on your behalf. Because it's isolated from your main browser, you log in only to the accounts you want the assistant

to access. Webhook triggers turn inbound events into proactive work. It generates secrets, starts the stack, and opens . Most local installs take a few minutes once Docker is running. **Or deploy on Railway:** **Connect a gateway** so CORE can run coding agents, drive your browser, and access local folders: **Requirements:** Docker 20. 20+, 4 vCPU / 8GB RAM Full self-hosting guide **Your first task (2 minutes after setup):** 1. Open the **Scratchpad** (your daily page at ) 2. Type or any

task you would normally do yourself 3. CORE picks it up within 3 minutes, gathers context from connected apps, and drafts a plan 4. 24%** average accuracy on the LoCoMo benchmark across single-hop, multi-hop, open-domain, and temporal reasoning. See the benchmark repo for full results and baseline comparisons. 3 in transit AES-256 at rest Your data is never used for model training Self-host for full isolation Security policy Vulnerabilities: harshith@poozle. We share the roadmap

and architectural decisions openly because the hardest problems in building a personal OS are best solved with the people using it. Star the repo, self-host it, share what you build, and open issues for what is broken or missing. ** Star this repo · Read the docs · Join Discord

Frequently asked questions

How many stars and forks are recorded?

RedPlanetHQ/core has 1,998 stars and 195 forks.

What is the repository rank?

RedPlanetHQ/core is ranked 9,122.

What language and category are recorded?

RedPlanetHQ/core has 1,998 stars, uses TypeScript and belongs to AI Engineering.

Which repository is closest in rank?

RedPlanetHQ/core is compared with patterns-ai-core/langchainrb, ranked 9,116 with 2,001 stars.

Nearby in the ranking
Similar items