aci
ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
Runs with mockssource: GitHubhomepagePythonApache-2.0commit 3e4a82fa5fd2
Python, Apache-2.0 licensed. The project labels itself: agents, ai, ai agents, api, developer tools, function calling, integration and llm.
aci runs, with stand-ins for the services it depends on. An Argusic agent installed it in 13 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Frontend npm dependencies installed, vitest test suite passes (3/3), dev server starts and responds (HTTP 307 redirect). Backend Python dependencies installed via uv sync, CLI loads fully, common module tests pass (11/11). Server integration and database-backed tests cannot run because PostgreSQL and Docker are unavailable in this container.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- PostgreSQL with pgvector extension is not available in this container — no docker, no postgres binaries, no root to apt install.13 minutes
- Frontend npm run build ran out of memory (OOM during Next.js production build).
- Backend server startup fails without LocalStack — check_dependencies() calls check_aws_kms_dependency() which needs a running AWS KMS mock.
- Install time
- 13 minutes
- Cold machine to finish
- 14 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- npm run test:run (frontend) exited 0, 3 tests passed; backend common tests: pytest aci/common/tests/ exited 0, 11 tests passed; npm run dev started and answered HTTP 307 on localhost:3000; python -m aci.cli --help printed all 11 CLI commands
- Model tokens used
- 118,447
- Exact commit tested
- 3e4a82fa5fd2
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
2026-11-07T22:30:57.712434Z ERROR codex_core::session: failed to record rollout items: thread 01a1b… tokens used 118,447 Here are my complete findings: **What works:** - Frontend: `npm install --legacy-peer-deps` — 889 packages installed. `npm run test:run` — 3/3 tes… - Backend: `uv sync` — all Python dependencies installed. Backend CLI (`python -m aci.cli --help`) … - Backend module `aci.server.config` loaded with env vars. `aci.cli` CLI loaded. **What's broken (blocked):** - No PostgreSQL server in the container — no Docker, no postgres binaries, no root to apt install. … - Frontend `npm run build` ran out of memory and crashed (OOM). Not required for dev test verificat… - Backend `aci.server.main` calls `check_dependencies()` → `check_aws_kms_dependency()` which requi…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 13 minutes to install, slower than the median of the 40 comparable projects Argusic has measured.
Of the 41 agents projects Argusic has installed and timed, aci was the 31st fastest to reach a running state, and 29 of 41 reached one at all.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.17 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.28 |
Topics (from GitHub)
agentsaiai-agentsapideveloper-toolsfunction-callingintegrationllmmcpoauth2open-sourcepermissionstoolsvibeops
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/aci)Questions
- Does aci run?
- aci runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 13 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test aci?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3e4a82fa5fd2. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test aci?
- The run that produced this verdict cost $0.17: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does aci take to install?
- 13 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does aci need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing aci?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does aci compare with the alternatives?
- Of the 41 agents projects Argusic has installed and timed, aci was the 31st fastest to reach a running state, and 29 of 41 reached one at all.
- Where is the evidence for aci?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.