DGC v0.51.0 is out
Navigate
Install DGC
A coding agent for the models you run

Own your coding agent.

A native agentic loop for local and API models, plus delegated turns through supported coding subscriptions. In your terminal and your editor.

$curl -fsSL https://vibedgc.com/install.sh | bash
Python 3.10+ · no root · local, API, and subscription routes
Ollamallama.cppvLLMLM StudioOpenAIAnthropicOpenRouterGroqDeepSeekClaude CodeCodexQwen CodeKimiGitHub Copilot
01 The CLI

A real agentic loop, in your terminal.

Reads, edits, runs the tests and self-corrects. Permission modes, plans, skills, hooks and a multi-agent fleet in one focused TUI.

FIG.1 · Agentic loopread → edit → run → verify · until the tests passillustrated run
fail → patch → rerun READread_file · grep EDITwrite · patch RUNgo test ./... VERIFYreal exit code ROUND 21 recovery round · suite passed
saved run · Go · alphametics
  1. 01readalphametics.go · tests2 files
  2. 02editcolumn backtracking solverfirst round
  3. 03runillustrative in-session testfirst round
  4. 04verifysuite still failingself-correct
  5. 05readresume · inspect rollbackline 137
  6. 06editpreserve winning assignmentfocused fix
  7. 07verifyisolated test suitepassed · 0.4 s

Drawn from a saved DGC run on go/alphametics: the first round failed its tests and the second passed. The in-session steps, their wording and their pacing are illustrative; the raw run output is not shown.

FIG.2 · Permission matrixShift + Tab cycles · /mode setsactual contract
Permission modes
ModeRead filesEdit filesShellUse it for
plan, read-only · proposes a planruns without askingunavailableunavailableUnderstand a codebase and review the proposal before model-requested edits or shell commands.
default, asks before writes and shellruns without askingasks firstasks firstEveryday work on a repository you care about.
acceptEdits, edits apply · shell still asksruns without askingruns without askingasks firstLong edit sessions where the diff is the review.
auto, model tool actions auto-approvedruns without askingruns without askingruns without askingUnattended work in a sandbox or throwaway repo; some integration prompts remain user-gated.
runs without asking asks first unavailablestanding rules: /permissions allow · ask · deny
dgc · scripted interface sequence

A small fix. A complete loop.

❯ Fix the clamp bounds and run the tests.
I’ll inspect the implementation and its tests first.
→ read_file clamp.py · test_clamp.py
✎ edit_file clamp.py
− return min(lower, max(upper, value))
+ return max(lower, min(upper, value))
$ bash python3 -m unittest -v
✓ 3 tests passed
Fixed the bounds. Values inside and outside the range now pass.
Edit & test
Scripted UI illustrations · native local/API workflows.
02 The extension

The same harness, native to your editor.

On native local/API routes: structured tools, readable diffs, goal-aware turns, permission decisions, and plan feedback. Subscription routes retain DGC's local goal record and presentation while the vendor owns its turn. A finished turn folds its work into one Worked for row, so it reads as your prompt and the answer.

FIG.3 · Editor surfaceActual extension · 0:31 · real timeVS Code · Cursor

Actual extension surface · deterministic protocol fixture · real disposable-file edit and unittest run · not a live model session · real time, no speed adjustment.

DGC · actual extension surface · 0:31

Actual extension surface · deterministic protocol fixture · real disposable-file edit and unittest run · not a live model session · real time, no speed adjustment.

Structured tools

Native-loop intent, target and result stay scannable.

Reviewable diffs

Additions and removals remain first-class.

Goal controls

Local record, timer, progress, pause and cancel at hand.

Native plan review

Approve, revise, or keep researching on local/API routes.

New in DGC 0.51

Your models, machines and tools in one place.

Choose a provider per chat, route helpers to the computers you choose, make pictures and clips with your generators, and use a plugin’s own card in the conversation. Each step keeps DGC’s review controls.

DGC · WORKThree ways to keep moving.
Illustrative demo · sample systems and media
/// DGCRouter2 systems · 3 workers free
Review the project with two helpers.
GPU boxExplorer · qwen3:8b · working
Mac StudioCritic · local model · working
This computer1 worker free

You choose the systems and models. Router is off until you turn it on.

DGC Router

Use your other model computers for helpers and Pips. See workers, model context and hardware where available.

Explore Router →

Images & video

Bring local or cloud generators. Keep results with the chat and in Library; review paid work first.

Explore image generation →

Plugin cards

Use a plugin’s own interface in Work, ChatDGC or Pips, and fold it away when you are done.

Explore plugin cards →

SDK 0.9

Bring Router, media generation, plugin cards and usage by system into your app.

Explore the SDK →

Providers

Keep hosts and a signed-in Claude Code or Codex in one list. Each chat and Pip chooses its own and keeps it after a reload.

Connect your model →

Trace

Replay what a reply did: each model round with its reported tokens, each tool with its own time. Nothing is guessed.

In your editor →

Queue and @ marks

A later message waits above the box to reorder, steer in or remove. Type @ to name a plugin, an Output, a Pip or a file.

The composer →

Pip workflows

Core proposes Personal Pips for your review. A workflow passes an exact result through two to four Pips, and grants none of them anything new.

Explore Pips →
02b Specialists

Named agents, with a face.

Explorer, researcher and critic are first-class task specialists. In the editor they land as coloured chips — the mark swirls while they work, stills when they finish. Click a chip for that agent’s own page: duration, answer, files. Child greps stay off the parent thread. A background task can outlive the turn; the composer stays free and DGC wakes a new turn when it lands.

map auth working
review findings finished
options research working
DGC · editor
Map auth and have a critic review the findings.
map auth working
review findings finished

Identity marks · live while working · click opens the agent page

Named types

Explorer maps. Researcher writes one findings file. Critic reviews it. Worker implements.

Living chips

Eight identity marks. Same face for the same id. Animate only while the agent is working.

Inner page

Back, duration, the child’s tools and a FILES card. Composer stays on the parent.

Background wake

A detached specialist keeps going after the turn ends. The pill stays; DGC starts a new turn when it lands.

03 DGC Pips

For the work
you come back to.

Give recurring reviews, focused fixes, test runs and the errands of your day a home of their own. Your Pips keep their own conversations, work with the models you choose, and bring decisions back to you. Review a team proposed by Core, then route results through a reviewed or bounded unattended workflow.

In the CLI, the VS Code extension and the SDK

04 Artifacts

Make something you can keep.

Documents, slides, spreadsheets, dashboards and pages. Choose an artifact in Work or ChatDGC, edit what DGC makes, and find it again in that surface’s Library. Compare changes, restore an earlier version, or export a file to share.

ON YOUR COMPUTER · SAVED VERSIONS · REAL FILE EXPORTS

This plan is one example of a Page artifact. Plans open privately on this computer; approval stays in DGC.

127.0.0.1:45000/plan/refactor-auth
/// PROPOSED PLAN

Refactor auth into its own package

Move token and verification helpers into one package and update the callers, without changing behavior.

  1. Create the package and move the helpers.2 files
  2. Re-export the public surface.1 file
  3. Update callers and run the suite.7 imports
Approve in terminal← → views · plan text saved
Artifacts in action

From the first draft to the file you send.

DGC · WORKBuild a dashboard, then find it again.
Illustrative demo · sample data
/// DGCWorkdeepseek-v4.1-flash
Build a dashboard for this week’s sales.
Artifact selected
Ask DGC to build, fix or explain…
+Artifact · Dashboard↗
ARTIFACT · DASHBOARD
Building a local preview

Documents and decks

Edit a document beside your chat or build a deck with layouts and speaker notes. Export Word, PowerPoint or PDF when it is ready.

Sheets you can work with

Edit cells and formulas, filter the rows you see and chart a selection. Export Excel or CSV, with the rows you filtered out still kept.

Dashboards over data you allow

Review each read-only source before it runs. Refresh locally without a model call, or ask a Pip to refresh after its run. Export HTML or PDF.

A history you can review

See who saved each version. Compare text, cells, slides or page files, then restore an earlier version without losing the newer one.

Explore Artifacts →

Mods

Make DGC fit how you work.

Small Python or TypeScript programs add status lines, panels, slash commands and guards. The same mod works in the terminal, Work, ChatDGC and the SDK. Review what it asks to read or do before you allow it.

DGC · MODSSmall tools inside your workflow.
Illustrative demo · no command runs here
/// DGCModsContext · running
Enabled ModsContext RunningTally RunningGuard Ready
CONTEXT MOD · LIVE PANEL

Know what fills the window.

52% used48% free

SystemToolsMessages

Context

See what fills the context window in a panel that follows each turn.

Tally

Count the steps DGC takes in this session, grouped by tool.

Guard

Hold a risky command for review and see why it needs your attention. A mod can stop an action or ask you; it cannot approve one for you.

Your own

Ask DGC to help write a mod, inspect its capabilities and try it in a development session. Each mod runs in its own sandbox.

Build with Mods →

Generative UI

Answers you can act on.

When a status report or comparison needs more than prose, DGC can arrange verified facts into metrics, steps, charts and choices in your editor. The answer is still readable as text, and a choice sends a normal message through your existing permissions.

DGC · GENERATIVE UIFrom an answer to the next request.
Illustrative demo · sample data
/// DGCWorkProject status
Summarize the release status and show my next choices.
✓ Ran test suite 24 passed
✓ Read release notes 4 files
Arranging an answer you can scan…

Click a choice in step 2 to try this illustration. On the website, no model request or tool action runs.

Work

See progress and test counts beside the familiar tool calls, agent map, Pip fixes and artifacts. DGC keeps their existing controls and motion.

ChatDGC

Compare options, scan a table, then choose a follow-up with one click. Widgets and saved artifacts keep their own tabs and Library.

Pips

Read an audit or a short plan in your Pip’s own conversation. A choice sends a message; proposals and approvals stay in their usual review flow.

Your app

The Python and TypeScript SDKs can read the same bounded cards as data. Render them in your interface and route choices through the regular SDK send path.

Explore Generative UI →

05 Providers

Point it at anything that serves a model.

Local inference, direct APIs, or a subscription you already pay for. Save several providers, choose a route for each Work session, and set a separate default for new sessions.

Local · on device

Your machine, your weights

Native chat or an OpenAI-compatible local server.

  • Ollamanative chat
  • llama.cppOpenAI /v1
  • vLLMOpenAI /v1
  • LM Studiolocal server
API · direct

Your chosen endpoint

DGC sends model-conversation context to the endpoint you configure. Optional integrations receive directed requests; language servers also receive queried document text.

  • OpenAInative
  • Anthropicnative
  • OpenRoutermulti-model
  • Groq · DeepSeekcompatible
Subscription · official CLI

Use the plan you have

The vendor’s binary keeps ownership of login and terms.

  • Claude CodePro / Max
  • CodexChatGPT
  • Qwen · Kimicoding plans
  • GitHub CopilotGitHub
06 Plugins, apps and MCP

67 plugins. One permission prompt.

A model on your own machine is not a model with fewer tools. Install a plugin from Settings or connect a server, and its tools join the same list as the built-ins: one route, one permission prompt, one set of hooks and redaction. And through three of them, Zapier, Composio and n8n, thousands more apps.

67
plugins in Settings
1
permission prompt, as for built-in tools
0
Node.js needed for hosted plugins

Logos belong to their owners.

Plugins

Install one, on the record

Every entry names its licence and, separately, what DGC actually verified — often less than “it works”.

Settings ▸ Pluginsdgc plugin install
Apps

Accounts you already have

GitHub, Notion, Linear, Sentry, Supabase, Stripe. Installed is not connected, and the model is told which.

browser sign-innamed token
Connectors

Many services, one server

Composio, Zapier, Arcade, Make, or n8n on your own instance. Several run the request in their own cloud — DGC says so before you connect.

mcp_searchrevoke upstream
MCP

The wire underneath

Stdio or remote, the 2026 protocol or the legacy handshake. Bounded frames, consent before any URL opens.

/mcpmcp__server__tool
07 Bring your own subscription

Already pay for a coding model? Run it here.

Pick the vendor in /connect. DGC passes each turn to its official CLI using that vendor account route—without configuring a separate DGC API key. Vendor plan, usage, and fee terms still apply.

Claude · ChatGPT

Your existing plan

Pro, Max, ChatGPT, and other supported first-party subscriptions.

Qwen · Kimi · Copilot

Official route

Each vendor binary owns authentication, account policy, and its model/tool turn.

DGC delegation

One place to start

DGC maps the mode, retains session history, runs SessionStart/Stop hooks, and presents the vendor’s result.

DGCpasses prompt + mapped mode
→
Official CLIowns sign-in, model + tools
→
DGCrecords and presents the result
ChatDGC

A chat for
everything else.

Ask anything that isn't code. It looks things up and cites every page, researches in depth, reads your files and draws the charts. Your own model answers, and your chats stay on your computer.

Meet Chat

In the DGC extension for VS Code and Cursor

From the founder
DGC’s bet is that the harness matters more than the model. We parse tool calls straight from the model’s text, so a local model with no function-calling API still runs the full read → edit → run → verify loop. The capability lives in the harness—not the weights.
FounderVibe DGC
08 Power tools

Built for real, long, autonomous work.

Optional modes for data-heavy tasks, verified unattended native-model runs, and turning your own sessions into scrubbed training data.

Persistent state

A Python workspace across turns

Load a dataset once, then operate on variables without repeating it into context.

Command: /code-action on
Native autonomous gate

Run until the check passes

On local/API routes, failures return to the next turn and completion waits for a real exit code. Delegated vendor turns bypass this gate.

Command: dgc --autonomous-gate "npm run check"
Trace → training

Your usage becomes your data

Export heuristic-filtered sessions as bounded, credential-scrubbed JSONL; review them before training.

Command: dgc export-training --successful-only
Checkpoints

Every turn is a point of return

Each turn DGC runs opens a recovery point—the exact conversation and the pre-edit bytes of every file the edit tools touch, saved before the tool runs. Rewind restores both, survives resume and compaction, and refuses a file-tool edit it cannot snapshot.

Command: /rewind
09 Focus pane

Keep working while it works.

A second surface under the transcript. Open the file explorer, browse and pick files for the next prompt, watch the model’s edits land—the agent never stops streaming above it. And a measured estimate of when the turn will finish, so you can walk away.

FIG.6 · Focus paneScripted interface sequenceTwo surfaces. One workflow.
dgc · scripted interface sequence
AGENT TRANSCRIPT

I’ll read the implementation and tests, then fix the bounds.

→ read_file clamp.py · test_clamp.py
FILESAgent working above · browse below
PROJECTclamp-demo/Current workspace
FILES
README.md · preview
# Clamp example

Keep a value within a range.

Run the tests:
python3 -m unittest -v
↑↓ browseEnter · add @pathq · return to prompt
❯Ask DGC anything…
Step 1 of 4 · Browse while it works
Scripted interface demo · explore the file names, or step through the sequence.

/files · a file explorer in the loop

Three columns, previews, copy/cut/paste, rename, trash with undo. Enter drops @path into your prompt; files the model changed this turn carry a mark.

Turn ETA · know when to come back

A range, not a promise: ~2–4 min left with the task count beside it, from this project’s own history and the turn’s task list. /eta stats reports how often it held.

/notify · walk away

A terminal notification, an editor toast, or your Stop hook when the turn ends. Your choice.

Native routes, real safety

Writes follow the permission mode and stay inside the project; nothing enters the model’s context unless you insert it. No shell, ever.

10 Live diff

See every change as it lands.

/diff opens a live view of everything the model has changed—every file with its added and removed line counts, and the diff itself—under the transcript while the turn keeps running. Select the lines you want to talk about and press Enter: they land in your next prompt as a quoted diff, so “why did you change these two lines?” quotes exactly those two lines.

FIG.7 · Live diffScripted interface sequenceRead. Select. Ask.
dgc · scripted interface sequence
AGENT TRANSCRIPT

I’ll inspect the bounds and make the smallest fix.

→ read_file clamp.py
DIFFWorking tree against HEAD · no changes yet
CHANGED FILES

No changes yet

clamp.py · working tree vs HEAD

Changes appear here as the agent edits.

Read-only view · your working tree stays unchanged
❯Ask DGC about a change…
Step 1 of 4 · Watch changes arrive
Scripted interface demo · click the changed lines to select them.

/diff · what changed, live

Git’s own answer, read-only: the working tree against HEAD, staged and untracked files, +12 −3 per file, the whole set summed in the header. Re-read every two seconds while it is open, so edits appear as they land.

Select lines → your prompt

Space starts a selection, Enter attaches it as a fenced diff block with the file and line range; a takes the whole hunk. Nothing else about the file enters the model’s context.

Side by side, or one at a time

Wide terminals show the file list and the diff together; narrow ones swap between them with Tab. J / K step through files without leaving the diff.

Looking, not committing

It never writes, stages or runs a shell command. Approving or undoing a turn stays with /review and the editor’s Changes view; /diff is for looking and asking while the work is still moving.

11 What’s inside

A complete harness, not a wrapper.

On native local and API routes, the model proposes while DGC orchestrates boundaries, execution, persistence, verification, and the evidence you review. Subscription routes delegate the model-and-tool turn to the vendor CLI.

FIG.5 · Native local/API pipelinethe model proposes · DGC orchestrates the loopstep 01 · prompt
Control

Gate the loop

Permission modes, plan review and thinking control.

permissionsplanthinking
Execution

Bound the work

Sandbox, MCP, artifacts and lifecycle hooks.

sandboxMCPhooks
Memory

Keep useful state

Standing goals, sessions, rewind and project memory.

/goalsessionsrewind
Scale

Run in parallel

Fleet sessions, isolated sub-agents and reusable skills.

fleettaskskills
From the founder

Why I built a coding agent for the models you run

It started with a usage limit, and a machine under my desk doing nothing.

Read the story →
DGC · real cloud-model capture · 0:48

Actual current DGC 0.51.0 full-screen TUI · real Ollama cloud run · deepseek-v4.1-flash:cloud · disposable controlled fixture · one-line code edit · python3 -m unittest -v passed 3/3 · real time, no speed adjustment · no user config or session persisted.