Can AdaL be vibe coded?
Coding agent that routes work to specialized workers across frontier model families
The core loop is genuinely reachable: open-source agents already route across model families, run tools, and edit repos, and a focused implementation of wiring gets you a personal version. What does not fall out of a focused implementation is the harness around the model, which is where AdaL claims its numbers come from, plus browser-based verification, clustered code review, and the team controls. You end up with an agent that works and a noticeably worse recovery rate on long tasks.
Jump to the build brief ↓Legacy-calibrated assessment
Checked Aug 2026
What you pay today, before any DIY hosting
medium editorial confidence
Tracked separately from the pricing check
Buildability by layer
Screens, forms, and focused interactions
The repeatable job the product performs
Availability and legality of required data
Uptime, queues, support, and maintenance
Security, compliance, and user confidence
The achievable core
- Wire a terminal agent to several provider APIs, give it file, shell and test tools, and let a planner sub-agent hand tasks to specialized workers in one session.
- Build the focused developer workflow you use repeatedly, with local configuration.
- A responsive interface with real empty, loading, success, and error states.
The parts a prompt cannot buy
- harness tuning: the planning, recovery and verification work that separates a demo agent from one that finishes long tasks
- browser-use verification of the app you just changed
- review clustering that groups a large diff into risk-ranked units
- one bill across every frontier provider instead of six metered API accounts
- The last 20 percent is sync, migration fidelity, speed, and edge cases.
- Connectors, OAuth flows, and vendor API changes require constant upkeep.
Build, switch, or keep paying
Narrower, with trade-offs
Wire a terminal agent to several provider APIs, give it file, shell and test tools, and let a planner sub-agent hand tasks to specialized workers in one session.
Use the build brief ↓3 checked options
- OpenCode ↗A terminal coding agent with no loyalty to any model vendor; you still pay the meter.
- Cline ↗An agent that lives in the editor you already use; the model bill is still yours.
- Goose ↗A desktop and terminal agent with real extension support, and no pretence that the model is free.
$20/mo
Because the gap between an agent that runs and an agent that finishes is mostly unglamorous harness work, and nobody wants to maintain it on a focused implementation. The flat subscription across every frontier model is the other half: DIY means holding API accounts with six vendors and watching the meter on every long run.
Visit AdaL ↗Why people still pay
Because the gap between an agent that runs and an agent that finishes is mostly unglamorous harness work, and nobody wants to maintain it on a focused implementation. The flat subscription across every frontier model is the other half: DIY means holding API accounts with six vendors and watching the meter on every long run.
The last 20 percent is sync, migration fidelity, speed, and edge cases.
Connectors, OAuth flows, and vendor API changes require constant upkeep.
The brief
Context, requirements, acceptance criteria, non-goals, and the full production standard — as Markdown, ready for any coding agent.
Build brief — a focused alternative to AdaL
Context
AdaL — Coding agent that routes work to specialized workers across frontier model families. It currently costs $20/mo.
The core loop is genuinely reachable: open-source agents already route across model families, run tools, and edit repos, and a focused implementation of wiring gets you a personal version. What does not fall out of a focused implementation is the harness around the model, which is where AdaL claims its numbers come from, plus browser-based verification, clustered code review, and the team controls. You end up with an agent that works and a noticeably worse recovery rate on long tasks.
This brief describes a focused, single-operator replacement for the part of AdaL that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.
What you are building
Wire a terminal agent to several provider APIs, give it file, shell and test tools, and let a planner sub-agent hand tasks to specialized workers in one session.
Build the focused developer workflow you use repeatedly, with local configuration.
A responsive interface with real empty, loading, success, and error states.
Requirements
Functional
Node 20 or Python 3.12.
Git repo to work against.
Playwright if you want the browser-verification worker.
Data and integrations
API keys for at least two providers in .env.
Each of these needs a real account, credential, or quota. Set them up before writing feature code.
Non-functional
Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
Security: server-side secrets, validated input, and no credentials in the client bundle.
Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
Portability: the operator can export their data and leave without losing it.
Implementation brief
Build me a multi-model coding agent CLI to replace AdaL, in an empty folder.
Stack: Python 3.12, one file per module, no framework.
Providers: Anthropic, OpenAI and Google, behind a single chat(model, messages, tools)
function. Keys from .env via python-dotenv, never hardcoded. A --model flag
switches families mid-session without restarting.
Tools the agent can call: read_file, write_file, list_dir, run_shell, run_tests.
run_shell prints the command and waits for y/n unless I pass --yolo.
An orchestrator loop: a planner call splits my request into numbered steps, then
each step runs as a fresh sub-agent with its own context window and only the tools
it needs. Sub-agent results append to a shared markdown scratchpad on disk.
Persist every session as JSONL under .agent/sessions/ so I can replay or resume.
A --resume <id> flag reloads the scratchpad and continues.
After any step that edits files, automatically run the test command from
pyproject.toml and feed failures back to the same sub-agent for one retry.
Print a running token and dollar total per provider at the end of every turn.
Out of scope, deliberately: browser automation, a GUI, team accounts, and any
hosted service. Those are the parts the subscription is actually selling.
README: setup, the .env template, how to add a fourth provider, and one honest
paragraph on where this loses to a tuned commercial harness on long tasks.
Delivery standard
Inspect the repository first, then write a short implementation plan before writing code.
Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
Add structured logs around every external call and return actionable errors without leaking sensitive details.
Write unit tests for the core logic and one automated test of the main user journey.
Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.
Acceptance criteria
A clean install starts the app using only the README and .env.example.
The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
Tests, type checking, linting, and a production build all pass with no ignored failures.
No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.
Non-goals
Do not build these, and do not claim to have replaced them:
Harness tuning: the planning, recovery and verification work that separates a demo agent from one that finishes long tasks.
Browser-use verification of the app you just changed.
Review clustering that groups a large diff into risk-ranked units.
One bill across every frontier provider instead of six metered API accounts.
SSO, SAML/SCIM, zero data retention and org-level model deny lists.
What you still own after launch
Secure credentials, rotate secrets, and handle provider rate limits.
Run migrations, backups, restores, and dependency updates.
Test the critical journey after every model, API, or hosting change.
Monitor failures and fix the edge cases a first prompt will miss.
Maintain every third-party integration as APIs and OAuth rules change.
Risk
Operational risk. The code is achievable; dependable data, integrations, and ongoing operations are the real cost.
Editorial confidence in this assessment: medium. No reviewed project implementation is linked yet.
Existing alternatives
Before building, compare these checked options:
OpenCode — A terminal coding agent with no loyalty to any model vendor; you still pay the meter
Cline — An agent that lives in the editor you already use; the model bill is still yours
Goose — A desktop and terminal agent with real extension support, and no pretence that the model is free
Prior art
Working open-source software you can read, fork, or borrow from before starting:
AdalFlow — The vendor's own open-source agent library; the building blocks are public even though the product is not
LiteLLM — One API shape over every provider, which is the boring half of model routing
Generated by Can It Be Vibe Coded? · Full report: https://www.canitbevibecoded.com/adal
You still own the product
- Secure credentials, rotate secrets, and handle provider rate limits.
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.
- Maintain every third-party integration as APIs and OAuth rules change.
Projects built from this idea
No reviewed implementation has been linked for AdaL yet. A submission is evidence for review, not automatic proof that the whole product was replaced.
Built a version of AdaL?Submit the project as evidence for this report.
Open-source prior art
Before you start
Can AdaL be vibe coded?
Partly, if you narrow it. The core loop is genuinely reachable: open-source agents already route across model families, run tools, and edit repos, and a focused implementation of wiring gets you a personal version. What does not fall out of a focused implementation is the harness around the model, which is where AdaL claims its numbers come from, plus browser-based verification, clustered code review, and the team controls. You end up with an agent that works and a noticeably worse recovery rate on long tasks.
What can an AI coding agent reproduce from AdaL?
Wire a terminal agent to several provider APIs, give it file, shell and test tools, and let a planner sub-agent hand tasks to specialized workers in one session. Build the focused developer workflow you use repeatedly, with local configuration. A responsive interface with real empty, loading, success, and error states.
What will a DIY AdaL replacement still be missing?
harness tuning: the planning, recovery and verification work that separates a demo agent from one that finishes long tasks; browser-use verification of the app you just changed; review clustering that groups a large diff into risk-ranked units; one bill across every frontier provider instead of six metered API accounts; The last 20 percent is sync, migration fidelity, speed, and edge cases.; Connectors, OAuth flows, and vendor API changes require constant upkeep.
What do I still own after building a AdaL alternative?
Secure credentials, rotate secrets, and handle provider rate limits. Run migrations, backups, restores, and dependency updates. Test the critical journey after every model, API, or hosting change. Monitor failures and fix the edge cases a first prompt will miss. Maintain every third-party integration as APIs and OAuth rules change.