LOCAL-FIRST • WORKS IN BACKGROUND

AI coding comes with overhead. Avorelo handles it.

Avorelo works seamlessly around your AI coding tool, handling what you would otherwise manage by hand. It keeps every run secure: secrets stay out of the model, prompt injection and exfiltration are blocked, and every file, network, and secret access passes a least-privilege boundary. It keeps context lean: feeding the model only what each task needs, so you spend fewer tokens. And it saves verifiable proof of exactly what changed, all automatic and in the background, across the tools you already use.

View on GitHub
npm install -g avorelo  ·  npm · Apache-2.0 · Contributing (DCO)
Open Source (Apache-2.0) · Runs locally, in the background · No account, backend, database, subscription, or telemetry.
Activate Avorelo where you already build
Avorelo works with Codex, Claude Code, Cursor, and local terminals. You run one local command in your project — there is no account to create and no credentials to manage.
  1. Run avorelo activate — in the project you are working in
  2. Avorelo detects and sets up your workspace — tools, guidance, and local state
  3. Keep using your coding agent — Codex, Claude Code, Cursor, or terminal
Activation runs entirely on your machine and creates local work receipts. It contacts no Avorelo service, and it does not send source code, prompts, diffs, env values, or secrets anywhere.
Public installation instructions will be published in the Apache-2.0 release.
Setup details & what activate does →
Dogfood

We build Avorelo with Avorelo. The automation layer that handles context, scope, proof, and handoff is the same layer we use to build this product every day.

Articles →
How it works

From setup to proof, handled in the background.

Activate once, locally. Avorelo understands your workspace, AI coding tools, project context, trusted skills, and safe working boundaries. Each session starts with the right work package: context, scoped access, checks, policies, and proof expectations. As work changes, Avorelo keeps the session on track, repairs scope drift before approval, handles safe fixes automatically, and captures proof at close. You keep working normally.

Without Avorelo

AI work starts from a blank prompt

  • You repeat project context again and again
  • Agents start without clear task boundaries
  • Skills, checks, and safety rules depend on manual prompting
  • Tool, file, or MCP access may be broader than needed
  • Proof is not planned before the work starts
With Avorelo

Every session starts ready for the actual task.

1
Project context is compiled automatically
Avorelo understands the repo, local state, task intent, relevant files, and supported AI coding tools.
2
The right work package is prepared
Avorelo prepares the context, relevant skills, checks, policies, scoped access, and proof expectations the task needs.
3
Safe defaults are set before work starts
File, tool, and MCP access begin focused on the task, with safer boundaries for secrets, network access, production changes, and risky actions.
Context ready Work package prepared Scoped by default
Without Avorelo

Mid-session work turns into babysitting

  • Context grows unmanaged as the session extends
  • Agents drift beyond the original task
  • Broad file, tool, or MCP access stays open by default
  • Routine corrections turn into approval noise
  • Duplicate work, repeated prompts, and retry loops pile up
  • It becomes hard to know what is safe, useful, or wasteful
With Avorelo

Your work continues. Avorelo keeps the session on track.

1
Routing adapts as the task evolves
The right model, tools, context, checks, and relevant skills stay aligned with the actual work, without manual prompting.
2
Scope is repaired before approval
Avorelo does not make you babysit agents. If the agent drifts beyond the requested work, Avorelo brings it back to the intended scope first and asks only when your authority is actually needed.
3
Safe fixes happen in the background
Routine corrections, access reduction, safe correction, validation checks, and duplicate-work prevention are handled without turning normal work into approval noise.
Session stays on track Scope repaired first Safe fixes handled
Without Avorelo

The session ends without usable proof

  • It is unclear what changed and why
  • Evidence is scattered across chats, commits, logs, and memory
  • Safe fixes and blocked risks are easy to miss
  • Follow-up work starts with missing context
  • Teams cannot clearly see what AI work actually produced
With Avorelo

Every session ends with proof you can use.

1
Outcomes are captured clearly
Avorelo records what was found, fixed, saved, proved, and what still needs attention.
2
Evidence is tied to the work
Checks, changed files, relevant skills, safe fixes, blocked risks, approvals, and validation signals are connected to the final outcome.
3
Value becomes visible
Individuals get clear local proof. Teams get outcome reporting on AI work, risk, savings, and completed value, without turning it into surveillance.
Proof at close Clear re-entry Visible value
What Avorelo automates

What you used to manage by hand.

Context, prompts, routing, access, proof, and handoff: the hidden overhead behind every AI coding run. Avorelo handles it automatically.

Manual overhead
Repeated context overhead

The same project context gets re-explained at the start of every run. Useful patterns from past sessions get lost between them.

Avorelo automates

Avorelo compiles useful context from previous runs and carries it forward, so the agent starts with what it actually needs.

Less repeated context
Manual overhead
Prompt and instruction overhead

Prompt structure, task boundaries, and working instructions get written from scratch each time or manually copied between sessions.

Avorelo automates

Avorelo structures task instructions and carries useful run patterns forward so each session builds on what worked before.

Better prompt carry-forward
Manual overhead
Model and tool selection overhead

Choosing the right model, tools, or capabilities for each task requires manual judgment or defaults to whatever was last active.

Avorelo automates

Avorelo routes each run to the right model and tools based on task signals, risk level, and required proof before the agent starts.

Fewer wrong-model paths
Manual overhead
Broad access and safety overhead

AI coding tools start with more file, tool, and MCP access than the task needs. Narrowing it takes manual effort or gets skipped entirely.

Avorelo automates

Avorelo scopes access to what the task actually needs before the run starts, and revokes it when the work is done.

Task-scoped access by default
Manual overhead
Proof tracking overhead

Tests pass, risks get blocked, and safe fixes get made. But nothing captures it in a form that is easy to review or reuse later.

Avorelo automates

Avorelo captures what was found, fixed, proved, and blocked at the end of each run, attached to the work that produced it.

Proof captured every run
Manual overhead
Handoff and re-entry overhead

When one session ends and another begins, useful state is effectively lost. The next run repeats the same setup instead of building on what was done.

Avorelo automates

Avorelo writes a clear handoff from each run so the next session starts with evidence and context, not a blank slate.

Clear re-entry
Already using Claude Code, Cursor, or Codex? Avorelo works alongside them - no workflow changes needed.
Workspace Safety

Avorelo lets AI coding agents work safely without making you babysit them.

Avorelo can act inside your workspace, so every run stays task-scoped, reversible, and backed by local proof. It detects scope drift before approval and asks only when your authority is actually needed.

Least privilege by default

Avorelo gives each run only the access it needs for the task. Files, tools, and MCP access stay scoped, with JIT access revoked when the work is done.

No silent workspace changes

Global config, hooks, MCP settings, model keys, env values, and secrets are never changed silently. Sensitive changes require clear approval.

Proof stays local

Session proof, handoff context, logs, and value signals stay on your machine unless you choose otherwise. Avorelo does not require cloud sync to prove what happened.

Scope drift is repaired first

If an agent expands beyond the task, Avorelo narrows it back before asking you to approve anything. You only step in when a real authority decision remains.

Licensing

Open Source under Apache-2.0. There is nothing to buy.

Avorelo is Open Source software under the Apache License 2.0. Personal, internal, organizational, and commercial use are all permitted — no fee and no separate license. See the license page.

Free and Open Source

Apache-2.0 grants broad rights to everyone: use, study, modify, and redistribute.

  • Personal, internal, and organizational use
  • Commercial use — permitted, at no cost
  • Modify and redistribute under Apache-2.0

Optional paid services

Support, implementation, integrations, training, and SLAs may be agreed separately — never required to use Avorelo.

  • Separate from the Apache-2.0 software rights
  • Scoped case-by-case; no public price list
  • Contact support@avorelo.com

Local by design

None of this needs a service. Avorelo runs on your machine, and the evidence it produces stays there.

  • No account and no hosted backend
  • No subscription and no account
  • No automatic telemetry