DEV Community

Cover image for Give your coding agent memory it can trust
Aviad Shakargy
Aviad Shakargy

Posted on

Give your coding agent memory it can trust

Your coding agent starts every session knowing nothing about your repository.

Then it guesses. Confidently.

It does not know where authentication actually lives. It does not know that your billing webhooks verify signatures, or that nobody ever wrote down why. It reads a few files, builds a story, and starts editing.

That is the problem I just shipped a fix for.

DevTime v0.1.2 turns local repository memory into an MCP server your agent can query.

If you are new here: DevTime is a local-first Engineering Intelligence CLI. It scans a repository and helps it explain itself from evidence. No cloud, no telemetry, no code execution during scan, no AI required.

GitHub logo Shakargy / devtime

Local-first Engineering Intelligence for software repositories.

DevTime

Local-first Engineering Intelligence for software repositories.

DevTime helps a codebase explain itself from evidence.

It scans code, tests, configs, routes, and decisions to identify supported software concepts, link claims to files, surface uncertainty, and warn about a narrow set of risky changes.

No cloud. No telemetry. No code execution. No AI required.

DevTime terminal demo - install, scan, and explain a repo from evidence

Prefer video? Watch the 2-minute demo: DevTime scans a repo locally, explains concepts from evidence, surfaces uncertainty, catches a risky diff, and shows how a corroborated decision improves understanding.


Try DevTime in 60 seconds

pipx install devtime-ei
dtc demo init
cd devtime-demo-saas
dtc init
dtc scan
dtc concepts
dtc explain "Billing Webhooks"
Enter fullscreen mode Exit fullscreen mode

The PyPI distribution is devtime-ei. The Python package remains devtime, and the CLI command remains dtc. dtc demo init copies a small static example repo into ./devtime-demo-saas so you can try DevTime without cloning this repository.

From source

git
Enter fullscreen mode Exit fullscreen mode


What Shipped in v0.1.2

One command:

dtc mcp start
Enter fullscreen mode Exit fullscreen mode

That runs a real MCP server over stdio, on your machine, exposing three read-only tools:

  • list_concepts - what the scanned repo supports, with confidence labels
  • explain_concept - the claims behind one concept, the evidence files, and what is still uncertain
  • get_context_pack - a governed context bundle to hand an agent before it touches code: supported claims, do-not-change-without-review paths, tests to run

So instead of your agent guessing where billing webhooks live, it can ask. And instead of getting a confident story, it gets claims with evidence paths and an explicit uncertainty list.

Try It in Two Minutes

Install with MCP support:

pipx install "devtime-ei[mcp]"
Enter fullscreen mode Exit fullscreen mode

Scan your repo:

cd your-repo
dtc init
dtc scan
Enter fullscreen mode Exit fullscreen mode

Hook it into Claude Code:

claude mcp add devtime -- dtc mcp start
Enter fullscreen mode Exit fullscreen mode

Or any client that reads a config file:

{
  "mcpServers": {
    "devtime": {
      "command": "dtc",
      "args": ["mcp", "start"]
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

No repo to test on? DevTime ships a demo:

dtc demo init
cd devtime-demo-saas
dtc init
dtc scan
Enter fullscreen mode Exit fullscreen mode

What the Agent Actually Gets

Here is the shape of an answer for a concept like Billing Webhooks:

  • Billing Webhooks is present and supported by behavior evidence. confidence 0.86
  • Evidence: src/billing/stripe-webhook.ts, tests/stripe-signature.test.ts
  • Uncertainty: no decision was found explaining key choices
  • Understanding Score: 58 / 100

Notice the last two lines. The tool tells the agent what it cannot prove. That is on purpose.

The Rules Did Not Change

Wiring a server is exactly the kind of moment where a tool quietly grows scope. This one did not:

  • Read-only. There are no write tools.
  • Local stdio only. There is no network listener.
  • No source code is returned. Claims, evidence file paths, and uncertainty. That is it.
  • Weak evidence produces uncertainty, not confidence.
  • If the repo was never scanned, the tools say so instead of making something up.

The main rule is still the same one DevTime started with:

No claim without evidence.

Agents are the exact audience that needs this rule. A human reviewer might notice when a summary smells wrong. An agent will happily build on it.

Where to Find It

DevTime is now listed in the official MCP Registry as:

io.github.Shakargy/devtime
Enter fullscreen mode Exit fullscreen mode

It is also on mcp.so and Smithery, and the package lives on PyPI as:

devtime-ei
Enter fullscreen mode Exit fullscreen mode

The Python import is still devtime and the command is still dtc. The name devtime was reserved on PyPI, so devtime-ei is the public distribution name.

Why I Keep Building This

AI tools write code faster than teams can understand it. The gap between "code exists" and "someone understands it" grows every sprint. Git remembers what changed. It does not remember what is true, what supports it, or what nobody ever decided.

AI writes. EI remembers.

That is the bet. v0.1.0 was the scanner. v0.1.1 made it installable in one line. v0.1.2 hands the memory to agents.

What I Want Feedback On

Not "nice project". This:

  • DevTime got a concept wrong on your repo
  • A claim is too strong
  • An uncertainty is missing
  • The MCP setup failed on your machine
  • Your agent got a context pack that misled it

Every one of these can become a regression fixture. That is how the tool earns trust: wrong outputs become tests that can never break again silently.

Links

GitHub logo Shakargy / devtime

Local-first Engineering Intelligence for software repositories.

DevTime

Local-first Engineering Intelligence for software repositories.

DevTime helps a codebase explain itself from evidence.

It scans code, tests, configs, routes, and decisions to identify supported software concepts, link claims to files, surface uncertainty, and warn about a narrow set of risky changes.

No cloud. No telemetry. No code execution. No AI required.

DevTime terminal demo - install, scan, and explain a repo from evidence

Prefer video? Watch the 2-minute demo: DevTime scans a repo locally, explains concepts from evidence, surfaces uncertainty, catches a risky diff, and shows how a corroborated decision improves understanding.


Try DevTime in 60 seconds

pipx install devtime-ei
dtc demo init
cd devtime-demo-saas
dtc init
dtc scan
dtc concepts
dtc explain "Billing Webhooks"
Enter fullscreen mode Exit fullscreen mode

The PyPI distribution is devtime-ei. The Python package remains devtime, and the CLI command remains dtc. dtc demo init copies a small static example repo into ./devtime-demo-saas so you can try DevTime without cloning this repository.

From source

git
Enter fullscreen mode Exit fullscreen mode

If you wire DevTime into your agent and it says something your repo cannot back up, open an issue. That is exactly the feedback I am looking for!

Top comments (0)