The bridge layer
CODENCER

The bridge between AI planners
and coding executors.

Open-source bridge. Local-first execution. Durable run record across any planner and any executor.

Try it locallyView on GitHub

v0.2.0-beta · Apache 2.0 · ★ 2 · CI green · last release 41 days ago

How this changes your day

Your AI coding workflow today, then with Codencer.

If you use more than one AI tool to ship code — a chat to plan, a coding agent to execute — you are the bridge between them. Codencer is what removes that copy-paste loop without taking either tool away.

Today

You are the bridge.

  1. You ask ChatGPT (or Claude, Gemini, DeepSeek) to scope a new feature.
  2. It replies with a 6-step plan.
  3. You copy step 1 into Claude Code (or Codex, Qwen) in your terminal.
  4. The coding agent works on it — edits files, runs its own checks, returns a summary.
  5. You read the summary, decide if it looks right, then go back to the chat.
  6. You paste the result, ask the chat what to do for step 2.
  7. Repeat for every step. You hold the plan in your head and shuttle context between two windows.

With Codencer

Codencer is the bridge.

  1. You ask the same chat to scope the same feature — Codencer is connected.
  2. The chat sends step 1 to Codencer. Codencer dispatches to your local coding agent.
  3. The coding agent runs in an isolated git worktree, on your machine, near the code.
  4. Codencer captures every artifact and returns a structured result to the chat.
  5. The chat reads the result and decides what's next. Codencer dispatches step 2.
  6. The loop continues without you holding state between two windows.
  7. You watch the run tree, review when it matters, work on something else when it doesn't.
What Codencer is

Bridge, not brain. State, not chat.

Codencer is an open-source coordination bridge that lets any AI planner — ChatGPT, Claude, Gemini, a human lead — dispatch real work to any AI coding executor — Codex, Claude Code, Antigravity, OpenClaw, Qwen — and produces a durable, auditable record of what happened.

We are not a coding agent. We do not run inference. We do not host the LLM. We sit between the planner and the executor as state, contract, and audit trail. Planning stays where it works best. Execution stays near the code. Codencer holds the part that doesn't exist anywhere else: the durable record across a heterogeneous fleet.

PlannerChatGPTClaudeGeminihuman
Codencerrunsstepsattemptsartifactsvalidationsgates
ExecutorCodexClaude CodeAntigravityOpenClawQwen
Bridge, not brain. State, not chat.
What this is, what this isn't

The neutral cross-vendor bridge
is still missing.

Vendors are deepening their own stacks — ChatGPT to Codex, Claude Desktop to Claude Code, Cursor to Cursor. Codencer is the bridge across all of them.

ProductPlannerExecutorCross-vendorAI coding semanticsLocal execSelf-hostDurable run recordAdapters shippedWorktree isolation
ChatGPT → CodexOpenAIOpenAI─chat only──chat history1─
Claude → CCAnthropicAnthropic─tool calls onlypartial─tool-call log1─
Cursor self-hostedCursorCursor─partial●●partial1─
Copilot cloudGitHubGitHub─partial──partial1─
DIY MCP glueanyanypartialyou build itvariesvariesyou build it0you build it
Codenceranyany●●●●●5●

Vendors deepen their own stacks. The neutral cross-vendor bridge with executor adapters and durable run records is still missing.

The model underneath

Three roles. Two contracts. One record.

The planner decides what to do. The executor does it. Codencer holds the durable run record between them. The state model — runs, steps, attempts, artifacts, validations, gates — is the asset.

Read the architecture →

What exists today

v0.2.0-beta on GitHub.

Browse the repo
  • Five beta tracks verifiedlocal daemon + CLI · self-host relay + connector · self-host cloud · planner-clients · provider connectors
  • Executor adapters liveCodex · Claude Code · Antigravity · Qwen — plus OpenClaw experimental
  • Durable state modelruns · steps · attempts · artifacts · validations · gates — SQLite-backed, worktree-isolated
  • Cross-platform CI greenmacOS · Windows · WSL/Linux at the v0.2.0-beta tag
  • Documentation discipline5,200+ lines across 30+ docs — every claim labeled proven, partial, compatibility-only, or deferred
  • Hardened by daily useThe founder runs Codencer every day across Mac, Windows, WSL/Linux, and remote VPS
Three ways to start

Try it. Wait for it. Read it.

Most people start with the OSS install. It's the fastest path to seeing the run record on your own machine. The hosted version replaces self-host when it ships in July. The docs are the deep reference for either path.

01

Install the OSS

Apache 2.0. Self-host on Linux, macOS, or WSL2. Native Windows is not supported for the daemon today.

What you need

  • Go 1.25+
  • git
  • C compiler (gcc/cc)
  • 5 minutes

No accounts, no LLM credits to start — simulation mode covers the canonical proof.

View the repo

02

The hosted version

Self-host today. A hosted Codencer launches July 2026 — one email when it opens, nothing before, nothing after.

03

Read the docs

Seven chapters covering the bridge model, the state model, executor adapters, self-hosting, and security.

Open the docs