agent-orcha

(★ 22)

Agent Orcha is a declarative framework designed to build, manage, and scale multi-agent AI systems with ease. Use YAML to orchestrate complex workflows, manage diverse tools via MCP, and integrate semantic search seamlessly.

Owner Repos

mlx-serve ★ 474

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.

Zig
spring-starter ★ 51

A spring-boot-starter application, with user authentication, registration, JPA using mysql.

Java
ghost-canvas ★ 20

AI-controlled visual design tool. LLM designs, humans view.

JavaScript
zigui ★ 12

A SwiftUI-like UI library in pure Zig — macOS/SwiftUI look across macOS, Linux, Windows

Zig
zig-ai ★ 9

Local AI desktop app: chat, image, video, TTS with voice cloning — all in-process, built with Zig

Zig

File Explorer

ZIP Download
  • .dockerignore
  • .gitattributes
  • .gitignore
  • .mcp.json
  • .npmignore
  • CHANGELOG.md
  • CLAUDE.md
  • docker-compose.nvidia.yaml
  • docker-compose.sandbox.yaml
  • docker-compose.yaml
  • docker-entrypoint.sh
  • Dockerfile
  • Dockerfile.nvidia
  • Dockerfile.sandbox
  • LICENSE
  • openapi.json
  • package-lock.json
  • package.json
  • playwright.config.ts
  • README.md
  • sandbox-entrypoint.sh
  • sandbox-jwmrc
  • sandbox-xresources
  • tsconfig.json

# Use via CDN

jsDelivr

jsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.

Link
Example

Command Glossary

Commands referenced in this DOCs, explained below.

🔍

docker run

View Details ▼

This command is an alias of `docker container run`.

tldr docker container run

View documentation for the original command:

🔍

done

View Details ▼

This shell keyword is used with `for`, `while`, `select`, and `until` to mark the end of a loop.

tldr for

View documentation for the `for` keyword:

tldr while

View documentation for the `while` keyword:

tldr select

View documentation for the `select` keyword:

🔍

gemini

View Details ▼

Launch an interactive prompt with Gemini AI.

gemini

Start a REPL session to chat interactively:

{{echo "Summarize the history of Rome"}} | gemini {{[-p|--prompt]}} -

Send the output of another command to Gemini and exit immediately:

gemini {{[-m|--model]}} {{model_name}}

Use a specific model (default: auto-gemini-3):

🔍

llm

View Details ▼

Interact with Large Language Models (LLMs) via remote APIs and models that can be installed and run on your machine.

llm keys set openai

Set up an OpenAI API Key:

llm "{{Ten fun names for a pet pelican}}"

Run a prompt:

cat {{path/to/file.py}} | llm {{[-s|--system]}} "{{Explain this code}}"

Run a system prompt against a file:

🔍

npm run

View Details ▼

Run a script.

npm run

List available scripts:

npm run {{script_name}}

Run a script:

npm run {{script_name}} -- {{argument}} {{--option}}

Pass arguments to a script:

🔍

npm start

View Details ▼

This command is an alias of `npm run start`.

tldr npm run

View documentation for the original command:

🔍

npx

View Details ▼

This command is an alias of `npm exec`.

tldr npm exec

View documentation for the original command:

🔍

openai

View Details ▼

CLI tool providing access to the OpenAI API.

openai api models.list

List models:

openai api completions.create --model {{ada}} --prompt "{{Hello world}}"

Create a completion:

openai api chat_completions.create --model {{gpt-3.5-turbo}} --message {{user "Hello world"}}

Create a chat completion:

🔍

tts

View Details ▼

Synthesize speech.

tts --text "{{text}}"

Run text-to-speech with the default models, writing the output to "tts_output.wav":

tts --list_models

List provided models:

tts --model_info_by_idx {{model_type/model_query_idx}}

Query info for a model by idx:

🔍

apt install

View Details ▼

Install packages for Debian-based distributions.

sudo apt install {{package}}

Install a package, or update it to the latest version:

sudo apt install {{[-V|--verbose-versions]}} {{package}}

Display verbose package version information during installation or update:

🔍

dnf install

View Details ▼

Install packages on Red Hat-based distributions.

sudo dnf {{[in|install]}} {{package1 package2 ...}}

Install packages by name:

sudo dnf {{[in|install]}} {{path/to/file}}

Install a package from a local file:

sudo dnf {{[in|install]}} {{https://example.com/package.rpm}}

Install a package from the internet:

🔍

ldd

View Details ▼

Display shared library dependencies of a binary.
Do not use on an untrusted binary, use objdump for that instead.

ldd {{path/to/binary}}

Display shared library dependencies of a binary:

ldd {{[-v|--verbose]}} {{path/to/binary}}

Display all information about dependencies:

ldd {{[-u|--unused]}} {{path/to/binary}}

Display unused direct dependencies:

🔍

pacman -S

View Details ▼

This command is an alias of `pacman --sync`.

tldr pacman sync

View documentation for the original command:

🔍

share

View Details ▼

Make local resource/filesystem available for mounting by remote systems.

share

List all currently shared filesystems:

share -F nfs -o rw /{{path/to/directory}}

Share a directory with read/write access:

share -F nfs -o ro /{{path/to/directory}}

Share a directory with read-only access:

// repository documentation