Get This Tool
Legioni
Summary
Most multi-agent coding setups dissolve between sessions — context evaporates, lessons learned get re-learned, and you start the next sprint from scratch. Legioni is an open-source agent team built on top of opencode that holds that context, coordinates specialist agents, and loops until the tests actually pass.
The orchestrator receives a plain-language task in opencode, breaks it down, and hands it to a chain of specialist agents — architect, implementer, reviewer, test-strategist — in sequence. Each step feeds the next; the loop closes only when tests pass. The 'lesson promotion' mechanism lets teams encode what they learn into persistent agent behavior, so the same mistake doesn't resurface two projects later. The hard boundary: Legioni runs inside opencode, full stop. If your team is not already on opencode or cannot adopt it, the architecture is irrelevant — there is no standalone path and no API to route through a different runtime.
Bottom line: Pick Legioni if your team already runs opencode and needs a structured, session-persistent agent loop for test-driven coding tasks; skip it if your stack is built around any other AI coding runtime, because there is no migration path.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Test-driven agent loop closes only when tests pass, so you are not manually checking whether the implementer's output actually works before shipping it to review.
- Specialist agents handle discrete roles — architecture, implementation, review, test strategy — which means a single task does not collapse into one undifferentiated prompt that loses track of constraints halfway through.
- Lesson promotion persists learned behaviors across sessions and projects, so teams stop re-encoding the same project rules every time they open a new task.
- Zero-install path via npx means you can run `legioni init` in a new repo without touching your global Node environment, keeping adoption friction low for the first experiment.
- MIT license and self-hosted operation mean the agents run entirely within your environment — no usage data leaves to a vendor API beyond whatever opencode itself sends.
Cons
Sign in to edit- Legioni is a hard dependency on opencode: every agent, every loop, every lesson runs inside opencode's runtime. Teams on Cursor, Cline, or any other AI coding environment cannot use this tool — the only path forward is adopting opencode first, which is a separate adoption decision with its own trade-offs.
- The project's public repository shows five commits and a small star count, which means edge cases in the agent loop, lesson promotion conflicts, and stack detection failures are under-documented and under-reported. Teams hitting unexpected behavior have no community issue history to search and no support channel beyond filing a GitHub issue themselves.
- Lesson promotion is a manual, explicit action — the agents do not automatically surface or apply learned behaviors without team intervention. Projects where nobody curates the promoted lessons see no compounding benefit across sessions, which makes the core differentiating feature opt-in rather than default.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- npm, Node.js
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- 2026-06-18T04:07:55.032Z
Best For
Who it's for
- Developers using opencode who want persistent multi-agent workflows
- Teams iterating on the same codebase over multiple sessions
- Projects requiring automated test generation and review loops
What it does well
- Automating multi-step coding tasks with test-driven verification
- Maintaining consistent agent behavior across projects via promoted lessons
- Coordinating specialist agents for architecture, implementation, review, and testing
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare Legioni
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Legioni free?
- Yes — Legioni is fully free to use. There is no paid tier.
- Is Legioni open source?
- Yes. Legioni is open source.
- Can I self-host Legioni?
- Yes. Legioni supports self-hosting on your own infrastructure.
- What platforms does Legioni support?
- Legioni is available on: npm, Node.js.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Legioni installs as an npm package and attaches to opencode as a team of coordinated coding agents. After running `legioni init` in a project directory — which detects the stack and compiles the agents — you address the orchestrator directly in opencode with a plain-language task. The orchestrator plans the work, routes subtasks to specialist agents (architect, implementer, reviewer, test-strategist), and loops until the tests pass. You watch the handoffs happen; you do not manually wire the pipeline.
The differentiating mechanism is lesson promotion. As agents complete tasks, the system allows teams to promote learned behaviors — patterns, constraints, project-specific rules — into persistent agent configuration. This means the agents on your third project carry the institutional knowledge from your first two, rather than starting from a blank context every time. For teams iterating on the same codebase across multiple sessions, this is the feature that separates Legioni from a one-shot code-generation prompt.
Legioni fits cleanly on a single-developer or small-team project where opencode is already the chosen coding environment and the goal is structured, test-verified iteration. It breaks down when the team needs to operate outside opencode — the docs describe no API surface, no webhook integration, and no adapter layer for other runtimes. The project’s GitHub page shows five commits and a star count in the single digits, which is accurate signal for where it sits on the maturity curve: functional, early, and not yet battle-tested at team scale.
Installation requires Node.js and a global npm install for the full feature set (promote, install, upgrade-team commands); `npx legioni init` works for one-off initialization without a global install. The agent workflow is defined as: orchestrator → architect → plan.md → implementer → code + tests → reviewer → passes or fails → test-strategist → edge cases + full suite → done.