sageroute

(★ 104)

Trajectory-aware model router. An OpenAI-compatible proxy that starts every task on a cheap model, watches what the agent actually does, and escalates on real execution evidence via the Levanto Sage API.

Owner Repos

agentic-stack ★ 2,231

One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when you switch.

Python
graph-engineering ★ 441

Graph engineering for AI agents: the 9-stage knowledge-graph pipeline (translated from SEU's graduate course) + task-graph orchestration patterns, as a Claude skill with teaching mode and paste-ready workflows
meridian-company-os ★ 326

No description provided.

TypeScript
ztk ★ 205

CLI proxy that reduces LLM token consumption by 78%+. Single Zig binary under 260KB. Zero dependencies.

Zig
agentic-harness ★ 84

Rust-native agent runtime, SDK, and CLI for software agents

Rust
brain ★ 77

Git-backed long-term memory for AI coding agents

Rust

File Explorer

ZIP Download
  • .dockerignore
  • .editorconfig
  • .env.example
  • .gitignore
  • CHANGELOG.md
  • CODE_OF_CONDUCT.md
  • CONTRIBUTING.md
  • Dockerfile
  • LICENSE
  • package.json
  • README.md
  • sageroute.config.example.json
  • sageroute.config.oauth.example.json
  • sageroute.daily.json
  • SECURITY.md
  • 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.

🔍

bun install

View Details ▼

Install JavaScript dependencies for a project from `package.json`.

bun {{[i|install]}}

Install all dependencies listed in `package.json`:

bun {{[i|install]}} {{package_name}}@{{version}}

Install a single package (this is an alias for `bun add`):

bun {{[i|install]}} {{[-g|--global]}} {{package_name}}

Install a package globally:

🔍

bun run

View Details ▼

Execute a JavaScript/TypeScript file, or a script from `package.json`.

bun run {{script_name}}

Run a script defined in `package.json`:

bun run {{path/to/file.ts}}

Run a JavaScript or TypeScript file directly:

bun run --watch {{path/to/file.ts}}

Run a file in "watch" mode (restarts automatically when the file changes):

🔍

bun test

View Details ▼

Run tests using Bun's built-in test runner.
It is a fast, Jest-compatible test runner that looks for `*.test.ts` (and similar) files.

bun test

Run all test files found in the project:

bun test {{path/to/file.test.ts}}

Run a specific test file or directory:

bun test --watch

Run tests in "watch" mode (re-runs automatically on file changes):

🔍

claude

View Details ▼

An agent-based coding tool that understands your code base and helps you code faster through natural language commands.

claude prompt

Execute with prompt:

claude update

Update `claude`:

claude mcp list

Get the list of specified MCP servers:

🔍

docker build

View Details ▼

Build an image from a Dockerfile.

docker build .

Build a Docker image using the Dockerfile in the current directory:

docker build {{github.com/creack/docker-firefox}}

Build a Docker image from a Dockerfile at a specified URL:

docker build {{[-t|--tag]}} {{name:tag}} .

Build a Docker image and tag it:

🔍

docker run

View Details ▼

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

tldr docker container run

View documentation for the original command:

🔍

git clone

View Details ▼

Clone an existing repository.

git clone {{remote_repository_location}} {{path/to/directory}}

Clone an existing repository into a new directory (the default directory is the repository name):

git clone --recursive {{remote_repository_location}}

Clone an existing repository and its submodules:

git clone {{[-n|--no-checkout]}} {{remote_repository_location}}

Clone only the `.git` directory of an existing repository:

🔍

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:

🔍

serve

View Details ▼

Static file serving and directory listing.

serve

Start an HTTP server listening on the default port to serve the current directory:

serve -p {{port}} {{path/to/directory}}

Start an HTTP server on a specific [p]ort to serve a specific directory:

serve {{[-C|--cors]}}

Start an HTTP server with CORS enabled by including the `Access-Control-Allow-Origin: *` header in all responses:

🔍

choice

View Details ▼

Wait for keypress and set `ERRORLEVEL` in batch scripts.

CHOICE "{{prompt}}"

Prompt for yes/no:

// repository documentation