DevCD mark
Local-first context layer for AI developers

Stop re-explaining.
Start from context.

Every new Claude, Copilot, or Codex session starts warm — with your current goal, last blocker, and do-not-repeat guidance — not a blank prompt and a recap request.

$ pip install devcd
Open Source Local-First No Telemetry Python 3.11+
devcd agentic action-packet
$ devcd agentic action-packet

▸ DevCD Action Packet  v0.2 · local · 2026-05-06
─────────────────────────────────────────────
Goal          Add memory TTL slice and tests
Last blocker  test_ttl_expiry resolved ✓
Next action   run make check → devcd quickstart
Do-not-repeat SliceService pattern — already applied
Withheld      12 raw log lines (policy: deny-raw)
─────────────────────────────────────────────
 Paste into your next agent session.
  The agent knows where you are. No recap needed.

DevCD

DevCD mark DevCD social avatar

## ⟩ What developers say about the problem

"Every new agent starts with a blank slate. You paste context. You explain what happened. You re-describe the task that was already described in three other places."

— DevCD VISION.md

"The next agent repeats failed attempts because it cannot see what already went wrong. Context is not portable, not structured, and not policy-governed."

— DevCD VISION.md

"AI agents should know what you are trying to continue without you having to tell them every time."

— Core Conviction, DevCD
## ⟩ What DevCD Does

Action Packet

Structured warm-start context for every new agent session. Goal, last blocker, do-not-repeat, and one next action—in a single policy-filtered payload.

Learn more →
🔒

Local-First Privacy

All context stays on your machine. No remote export, no telemetry, no cloud sync by default. You decide what gets shared and with whom.

Policy docs →
📋

Policy Receipts

Every observation and every withholding is logged with a policy receipt. You always see exactly what was included in a handoff—and what stayed out.

Read more →
🔌

MCP Server

Native Model Context Protocol server for direct agent consumption. Any MCP-capable agent reads your local DevCD context without you pasting anything.

Agent docs →
🤝

Works With All Agents

One command configures Claude, GitHub Copilot, Codex, and OpenClaw at once. All your agents start warm from the same local context source.

Agent landscape →
🖥️

CLI + HTTP API

Full-featured CLI backed by a local HTTP API. Use it interactively, in scripts, or from any tool that speaks HTTP on localhost.

Architecture →
## ⟩ Works With
Claude GitHub Copilot OpenAI Codex OpenClaw Cursor Any MCP Agent
## ⟩ Quick Start
1
Install pip install devcd
2
Setup your workspace devcd setup --yes
3
Read the Action Packet devcd agentic action-packet
## ⟩ Why DevCD
Trust by default

Local-first defaults, explicit policy receipts, and visible withheld-context boundaries on every handoff.

No recap tax

The next agent reads the Action Packet instead of asking you to re-explain your last three hours of work.

Safe to share

Goal, blocker, do-not-repeat, one next action, and context-load hints—nothing raw, nothing that shouldn't travel.

DevCD is not another agent to run. It is the layer that lets the next agent resume instead of restart.