You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: CLAUDE.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,15 +4,15 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
4
4
5
5
## Project Overview
6
6
7
-
AgentSync is a headless MCP server for AI agent team coordination. It solves state synchronization when multiple people work through AI agents (Claude Code, etc.) on the same codebase simultaneously — preventing file conflicts, tracking work in flight, and managing task dependencies.
7
+
Swarm Protocol is a headless MCP server for AI agent team coordination. It solves state synchronization when multiple people work through AI agents (Claude Code, etc.) on the same codebase simultaneously — preventing file conflicts, tracking work in flight, and managing task dependencies.
8
8
9
9
**Status:** Alpha — all 19 MCP tools implemented, integration tests written. See SPEC.md for the full design.
10
10
11
11
## Philosophy & Positioning
12
12
13
13
This is a **coordination protocol, not a project management tool**. The origin insight: "Jira was built for humans clicking buttons. This is coordination infrastructure for agent-first teams." The problem isn't Kanban or sprints — it's state synchronization when agents are the primary interface.
14
14
15
-
**Key differentiator:** Every existing tool (Claude Code Agent Teams, CCPM, tick-md, Agent-MCP, 1Code, etc.) solves single-developer multi-agent coordination. AgentSync solves multi-human multi-agent coordination across teams. See LANDSCAPE.md for the full competitive analysis.
15
+
**Key differentiator:** Every existing tool (Claude Code Agent Teams, CCPM, tick-md, Agent-MCP, 1Code, etc.) solves single-developer multi-agent coordination. Swarm Protocol solves multi-human multi-agent coordination across teams. See LANDSCAPE.md for the full competitive analysis.
16
16
17
17
When making implementation decisions:
18
18
-**Protocol over product.** Keep it minimal and composable. Resist feature creep toward traditional PM concepts (sprints, boards, velocity, story points).
@@ -38,7 +38,7 @@ npm test # run integration tests (needs PostgreSQL)
38
38
npm run dev # watch mode for TypeScript compilation
39
39
```
40
40
41
-
Database: PostgreSQL on `localhost:5432`, database `agentsync`. Schema auto-applies on startup via `initDb()`. Connection string via `DATABASE_URL` env var (default: `postgresql://postgres:postgres@localhost:5432/agentsync`).
41
+
Database: PostgreSQL on `localhost:5432`, database `swarm_protocol`. Schema auto-applies on startup via `initDb()`. Connection string via `DATABASE_URL` env var (default: `postgresql://postgres:postgres@localhost:5432/swarm_protocol`).
42
42
43
43
Tests: Vitest, integration tests against real PostgreSQL. No mocks. Run `npm test` — requires a running PostgreSQL instance.
@@ -107,7 +107,7 @@ See [SPEC.md](SPEC.md) for the full design. See [LANDSCAPE.md](LANDSCAPE.md) for
107
107
108
108
Every tool in this space — Claude Code Agent Teams, CCPM, tick-md, Agent-MCP, 1Code — solves the **single-player** version: one dev running multiple agents in parallel. That's useful but insufficient.
109
109
110
-
AgentSync solves the **multiplayer** version: multiple humans, each working through agents, across teams. Cross-human conflict detection, dependency chains that auto-unblock, context packages that onboard agents instantly.
110
+
Swarm Protocol solves the **multiplayer** version: multiple humans, each working through agents, across teams. Cross-human conflict detection, dependency chains that auto-unblock, context packages that onboard agents instantly.
111
111
112
112
See [LANDSCAPE.md](LANDSCAPE.md) for the full competitive breakdown.
0 commit comments