talkcody

TalkCody - Code is cheap, show me your talk. 🚀 Free Open Source AI Coding Agent.

Runs with mockssource: GitHubhomepageTypeScriptMITcommit 5543bf926436

TypeScript, MIT licensed. The project labels itself: ai agents, coding agent, coding assistant, rust, tauri2 and vercel ai sdk.

talkcody runs, with stand-ins for the services it depends on. An Argusic agent installed it in 25 minutes and hit 4 errors on a clean machine with no GPU, and the whole session was recorded.

Bun/Node/Rust toolchain installed user-level; frontend builds and its 2845 tests plus 99 API tests pass against a local Turso mock; the API server answers 200 on /health and /api/remote-agents/configs; only the Tauri desktop binary could not be built because glib-2.0/webkit2gtk dev packages are missing and cannot be installed without root.

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 87 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
87 / 100
cost of the verifying run
$0.40 (measured)
recorded runs
1
last tested
stars
480
forks
78
open issues
8
watchers
11
size
10 MB
created
last push

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.

Time lost to each failure while testing talkcody, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • auth-google.test.ts 'should redirect to Google' failed (400): app.request(path,{env}) does not pass env into c.env in Hono 4.10.312 minutes
  • apps/api 'bun run test' always failed: run-tests.ts spawns 'bun run test <files>' recursively, then production URL equals test URL and safety check aborts10 minutes
  • Bun not installed (also no unzip binary); Node 18 too old for jsdom 28 (@exodus/bytes ERR_REQUIRE_ESM); rustup lacking; all fixed by user-level installs6 minutes
  • Tauri/Rust desktop build cannot compile: glib-2.0 and webkit2gtk-4.1 dev packages absent (only runtime .so, no .pc), no root to install system packages5 minutes
Install time
25 minutes
Cold machine to finish
24 minutes
Errors hit and fixed
4 hit, 3 fixed with no human help
How the result was proved
'bun run test' exited 0 (258 files, 2845 tests passed); 'cd apps/api && bun run test' exited 0 (15 pass); 'bun test src/test/*.test.ts' 99 pass 0 fail; curl /health returned 200 with database connected; bun run build exit 0 (built in 20.65s); docs next start served 200 'Welcome to TalkCody'
Model tokens used
1,914,041
Exact commit tested
5543bf926436
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

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

All verification complete. Here is the final report.
**Summary of what I did and observed**
1. **Install** (`bun install` → 921 packages, docs `bun install` → 421 packages). Toolchain gaps fi…
2. **Bugs found and fixed**:
   - `apps/api/src/test/run-tests.ts` spawned `bun run test …` recursively, so the documented `cd a…
   - `apps/api/src/test/auth-google.test.ts` passed env via `app.request('/api/auth/google', { env …
3. **Verification run**:
   - `bun run test` (root): 258 files, 2845 tests passed, exit 0.
   - `bun run lint`: 697 files checked, exit 0. `bun run type-check`: exit 0. `bun run build`: buil…
   - `cd apps/api && bun run test`: 15/15 pass; full API suite `bun test src/test/*.test.ts`: 99 pa…
   - API server on :3000: `GET /health` → 200 `{"status":"ok","database":"connected"}`, `/api/remot…
   - Vite dev server: HTTP 200. Docs site `bun run build` exit 0; `next start` → HTTP 200 serving "…

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

  • Licensed MIT, as reported by its host.

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 25 minutes to install, slower than the median of the 123 comparable projects Argusic has measured.
  • Hit 4 errors during setup, 1 of which were not solved.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 124 ai-agents projects Argusic has installed and timed, talkcody was the 109th fastest to reach a running state, and 96 of 124 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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs with mocks87.000.40

Topics (from GitHub)

ai-agentscoding-agentcoding-assistantrusttauri2vercel-ai-sdk

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/talkcody.svg)](https://argusic.com/subject/talkcody)

Questions

Does talkcody run?
talkcody runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 25 minutes, hitting 4 errors on the way, and recorded the session.
How did Argusic test talkcody?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5543bf926436. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test talkcody?
The run that produced this verdict cost $0.40: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does talkcody take to install?
25 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 talkcody need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing talkcody?
4 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 talkcody compare with the alternatives?
Of the 124 ai-agents projects Argusic has installed and timed, talkcody was the 109th fastest to reach a running state, and 96 of 124 reached one at all.
Where is the evidence for talkcody?
The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion