https://github.com/cesp99/spettro
Spettro is a terminal coding assistant built in Go. It automates planning, coding, and testing with multi-agent workflows, model selection, and an intuitive UI. Connects to local and remote AI providers, supports conversation history, and empowers developers to streamline their workflow from the terminal.
https://github.com/cesp99/spettro
ai ai-agent ai-agents bubbletea cli coding-agent go local multi-agent terminal tui
Last synced: 22 days ago
JSON representation
Spettro is a terminal coding assistant built in Go. It automates planning, coding, and testing with multi-agent workflows, model selection, and an intuitive UI. Connects to local and remote AI providers, supports conversation history, and empowers developers to streamline their workflow from the terminal.
- Host: GitHub
- URL: https://github.com/cesp99/spettro
- Owner: cesp99
- License: gpl-3.0
- Created: 2026-03-13T10:22:11.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2026-05-30T18:35:29.000Z (26 days ago)
- Last Synced: 2026-05-30T20:14:58.405Z (26 days ago)
- Topics: ai, ai-agent, ai-agents, bubbletea, cli, coding-agent, go, local, multi-agent, terminal, tui
- Language: Go
- Homepage: https://spettro.eyed.to
- Size: 1.2 MB
- Stars: 15
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Funding: .github/FUNDING.yml
- License: LICENSE
- Agents: AGENTS.md
Awesome Lists containing this project
README
# Spettro
[](https://go.dev/)
[](https://github.com/charmbracelet/bubbletea)
[](#provider-setup)
[](#)
[](LICENSE)
[](https://deepwiki.com/cesp99/spettro)
CA: C3fawupKrXdn3X7KPTmmnkwzJQ9qycMNag55ZzQ8pump
Spettro is a terminal-first multi-agent coding assistant written in Go.
It uses a configurable agent manifest (`spettro.agents.toml` + `agents/*.md` prompts), parallel sub-agent spawning via `TOOL_CALL` and an `agent` tool, plus specialized orchestrator/worker roles (plan, coding, ask, explore, code, git, test, review, docs).
## Highlights
- Configurable multi-agent system via `spettro.agents.toml` and `agents/*.md`
- Parallel `TOOL_CALL` spawning of sub-agents
- Permission policies: `ask-first`, `restricted`, `yolo`
- Live tool traces in planning/coding runs
- Fantasy-backed provider routing for OpenAI, Anthropic, and OpenAI-compatible text calls
- Multi-provider model support via `models.dev` catalog + OpenAI-compatible endpoints
- Anthropic [extended-thinking levels](docs/thinking.md) (`/thinking off|low|medium|high|x-high`)
- Conversation persistence and resume per project
- Project trust prompt before first use in a folder
## Build and run
Requirements:
- Go `1.26.1+`
```bash
git clone https://github.com/cesp99/spettro
cd spettro
make build
./bin/spettro
```
Alternative:
```bash
go run ./cmd/spettro
```
## First-time setup
At first launch:
1. Confirm folder trust.
2. Run `/connect` to add an API key (or local endpoint).
3. Run `/models` to select provider/model.
4. Start with `plan` (default agent) and switch with `Shift+Tab`.
## Common commands
Spettro commands are entered with a leading `/`.
- `/help` show help text
- `/exit`, `/quit` quit Spettro
- `/mode`, `/next` cycle active agent/mode
- `/connect` connect provider or local endpoint
- `/models [provider:model] [api_key]` open selector or set directly
- `/permission ` set execution policy
- `/permissions [ask-first|restricted|yolo]` show/set permission policy
- `/permissions debug ` toggle permission diagnostics
- `/budget ` set request token budget (`0` = unlimited)
- `/thinking ` set extended-thinking budget (Anthropic Claude Opus/Sonnet; ignored by providers without thinking)
- `/plan [prompt]` switch to plan mode or run plan prompt
- `/approve` execute pending approved plan through coding agent
- `/tasks [list|add|done|set|show]` manage session tasks
- `/mcp ` manage MCP resources and auth tokens
- `/skill ` manage Agent Skills (Claude Code / OpenAI / Anthropic format)
- `/hooks` show effective runtime hooks
- `/compact [focus]` summarize conversation history
- `/compact auto ` configure auto-compact
- `/compact policy` show compact thresholds/counters
- `/clear` auto-save and clear current conversation
- `/resume` load a previous saved conversation
- `/init` analyze the repo and create/update `SPETTRO.md`
- `/remote [:port]` expose a loopback HTTP/SSE control plane (see [`docs/remote.md`](docs/remote.md))
- `/remote local [:port]` expose the control plane to LAN devices on `0.0.0.0` (see [`docs/remote.md`](docs/remote.md))
- `/telegram setup ` configure a Telegram bot relay so you can drive Spettro from a chat (see [`docs/telegram.md`](docs/telegram.md)). Alias: `/tg`.
For full commands and keybindings, see [`docs/commands.md`](docs/commands.md).
## Project docs
- [Agent Manifest](AGENTS.md)
- [Agent Prompts](agents/README.md)
- [Agent Skills](docs/skills.md)
- [Getting started and workflow](docs/getting-started.md)
- [Commands and keybindings](docs/commands.md)
- [Configuration and storage](docs/configuration.md)
- [Architecture overview](docs/architecture.md)
- [Remote control plane](docs/remote.md)
- [Telegram relay](docs/telegram.md)
- [Extended thinking levels](docs/thinking.md)
- [Troubleshooting](docs/troubleshooting.md)
- [Documentation Index](docs/README.md)
## Development
```bash
make test
make build
make build-all
```