Spettro Agent · Multi-agent terminal coding

Terminal-first. Multi-agent. Open source.

The terminal coding assistant with real agent handoffs.

Spettro Agent is a Go + Bubble Tea TUI with manifest-driven agents, approval-aware execution, encrypted keys, and provider routing across Anthropic, OpenAI-compatible, and local model endpoints. Plan, approve, code, and resume — without leaving the terminal.

Explore the repo ↗ See what's inside

Install the Spettro Agent CLI

$ curl -sSfL https://raw.githubusercontent.com/cesp99/spettro/main/install.sh | sh
cesp99/spettro · @SpettroAgent · DexScreener · Docs
$ spettro — ~/cesp99/spettro
LIVE
spettro
Spettro Agent v0.4.1 · multi-agent terminal assistant
Project trust: ✓ ~/cesp99/spettro

plan Analyzing repository structure…
Found 47 Go files, 3 agent manifests
Loading spettro.agents.toml → plan, coding, review

plan → Proposed: refactor provider routing layer
3 files · ~120 lines affected

/approve
code Executing plan…
provider/router.go modified
provider/catalog.go created
Session saved · /resume to continue
codingplancoderesume

Shipped, not pitched

Real repo. Real workflow. Real builders.

Numbers come straight from the public repository, the release feed, and the docs — nothing else.

Go 1.26
Bubble Tea TUI
Built for the terminal.
GPL 3.0
Open source.
Source on GitHub.

Product

Built around repository work, explicit permissions, and real agent handoffs.

Spettro Agent is not trying to hide the workflow. The product is the workflow: trust the folder, connect a model, plan the change, approve execution when needed, and keep the session alive long enough to finish serious work.

trust

Explicit project trust handshake before any tool call leaves the terminal.

plan → code

Plan agent proposes, coding agent executes — only after /approve in stricter modes.

resume

Sessions, tasks, /clear, /resume, /compact. Long threads stay workable.

no lock-in

Anthropic, OpenAI-compatible, or local. Model catalog cached from models.dev.


Inside Spettro Agent

Every part of the workflow is a first-class surface.

Manifest-driven agents, approval flow, provider routing, encrypted keys, hooks, MCP, and a project indexer — all in one terminal-native runtime.

live

Multi-agent runtime

Manifest-driven roles for plan, coding, review, docs, git, test, and explorer agents — handoffs are explicit, not hidden behind a single prompt.

live

Approval-aware execution

Ask-first, restricted, and yolo permission modes. Plans pause before execution and resume only after /approve.

native

Provider flexibility

Native Anthropic, OpenAI-compatible APIs, and local endpoints like LM Studio or Ollama. Models.dev catalog cached locally.

native

Encrypted key storage

API keys are encrypted with AES-GCM. Trusted paths, sessions, and cached models live under ~/.spettro.

live

Sessions, tasks, compact

Persistent session storage for messages, tasks, and agent events. /clear, /resume, and /compact keep long threads alive.

native

Per-repo agent manifests

Project-level spettro.agents.toml plus prompt files in agents/ — each repo can define its own default agent and runtime.

live

Hooks + command policy

PreToolUse, PostToolUse, PermissionRequest, and SessionStart hooks. Persisted command approvals in .spettro/allowed_commands.json.

live

MCP + project indexer

MCP integration and a project indexer keep agents grounded in repo state instead of guessing from filenames alone.


Workflow

From trust to resume, in five steps.

The default Spettro Agent flow is documented and predictable. No black-box agents, no surprise file writes, no vendor lock-in.

01· trust

Trust the project

Spettro Agent starts with an explicit project trust handshake. Path-scoped permissions, no implicit access.

02· connect

Connect a model

/connect adds a provider — hosted Anthropic, OpenAI-compatible, or a local OAI endpoint. Keys are encrypted.

03· plan

Plan first

The plan agent reads the repo and proposes a change. You approve before any code is written.

04· code

Approve and code

Coding agent executes the queued plan. Tool calls are visible. Permission level is yours to choose.

05· resume

Resume later

Sessions persist. /compact summarises context, /resume picks the work back up next time you open it.


Why Spettro Agent

The terminal coding assistant, as a real workflow.

Single-agent terminal assistants collapse the whole job into one prompt. Spettro Agent splits the work into roles you can see.

Spettro Agent Single-agent CLI Editor chat
Multi-agent roles Built in One role pretending to be many Editor with chat
Approval flow Ask-first / restricted / yolo Per-tool prompt Per-tool prompt
Provider routing Anthropic + OAI + local Vendor-locked Vendor-locked
Per-repo manifests spettro.agents.toml Global config only Workspace settings
Persistent sessions Sessions, tasks, compact Chat history Chat history

Docs

Everything important is already documented.

The repo ships its own docs. DeepWiki keeps a structured map of the codebase, including the agent runtime, provider layer, and storage model.

Getting started Commands Configuration Architecture Troubleshooting DeepWiki

FAQ

Questions that come up once you start using it for real work.

What makes Spettro Agent different from a single-agent terminal assistant?
Spettro Agent is built around explicit roles and handoffs. Planning, coding, review, docs, git, test, and explorer agents can each own part of the work instead of one assistant pretending to do everything the same way.
Does it support local models?
Yes. The docs cover OpenAI-compatible local endpoints such as LM Studio or Ollama, alongside hosted providers.
How does approval work?
Spettro Agent exposes ask-first, restricted, and yolo permission modes. In stricter flows, plans pause before execution and continue only after approval.
What does first-time setup look like?
Launch Spettro Agent, confirm project trust, run /connect to add an API key or local endpoint, run /models to select a model, then start in plan mode.
Can I resume longer conversations later?
Yes. The docs describe persistent session storage for messages, tasks, and agent events, plus /clear, /resume, and /compact so longer threads stay manageable instead of vanishing.
Are API keys stored in plain text?
No. Keys are encrypted with AES-GCM and are not stored in plaintext inside config.json.
Can I customize the agent workflow per repository?
Yes. Spettro Agent can load a project-level spettro.agents.toml and prompt files in agents/, so each repository can define its own default agent, runtime settings, and handoff structure.

Get the source

Open the repo. Read the docs. Run it locally.

Free, open source, GPL-licensed. Spettro Agent is built for developers who want a terminal assistant with explicit roles, approval flow, and provider freedom.

Install the Spettro Agent CLI

$ curl -sSfL https://raw.githubusercontent.com/cesp99/spettro/main/install.sh | sh
Source on GitHub ↗ Read the docs
Release notes · GPL 3.0 License · cesp99/spettro