Consensus
io.github.masterblaster14Published by GitHub account masterblaster14v0.1.0Updated Oct 27, 2026
Coordination for AI coding agents: declare plans, catch design conflicts early, share team memory.
Overview
Coordination server for teams of AI coding agents: agents declare plans before writing code, get a proceed/wait verdict, and share team memory.
- What you can do
- Declare a coding plan and get a verdict (proceed, proceed with context, or wait) checked against other in-flight plans and prior rulings
- Check verdicts and withdraw a claim when a plan changes or is abandoned
- Query shared team memory and record discoveries, decisions and dead ends
- File handoffs describing what changed, what was left alone and what was assumed
- Read status and report usage for the connected developer's key
- When to use it
- Useful when several developers each run an AI coding agent on the same codebase and want design conflicts caught before code exists, plus shared memory so agents do not repeat the same reading and dead ends. Also relevant for teams wanting human rulings applied automatically to future conflicting plans.
- Requirements
- Remote MCP endpoint over streamable HTTP; a personal API key from the Consensus settings page sent as an Authorization bearer header. A Consensus account (GitHub or email sign-in) and an organisation; optional GitHub and Notion integrations. Self-hosting needs Python 3.11, PostgreSQL with pgvector and Redis.
Installation
In SourceWeft
- Open Consensus in the dashboard and add it to a workspace.
- Connect Authorization token credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.masterblaster14%2Fconsensus/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"consensus": {
"type": "http",
"url": "https://consensus-production-aed6.up.railway.app/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}README
Consensus
Coordination for teams whose developers each run an AI coding agent on the same codebase.
Before an agent writes code, it declares its plan. Consensus checks that plan against every other plan in flight and against what the team already knows, and answers in a second: proceed, proceed with context, or wait.
Why
AI coding agents are fast and they work alone. On a team that produces two problems git cannot see:
- Design conflicts in files that never touch. One agent moves sessions to signed tokens; another adds a login endpoint that assumes server-side sessions. No merge conflict. Two incompatible designs discovered days later in review.
- Every agent starts from zero. The same code gets re-read, the same dead ends get re-tried, and nothing one agent learns reaches the next.
What it does
- Declare before writing. Plans are compared on what they mean, not which files they touch. Conflicts are caught before the code exists.
- Shared memory. Agents ask what the team knows before reading the codebase, and record discoveries, decisions and dead ends as they work.
- Human rulings that compound. When two plans genuinely conflict, a person decides once. The ruling is stored and applied automatically to every future plan that would raise the same conflict.
- Clean handoffs. When work is done, the agent files what changed, what it left alone, and what it assumed. That becomes the pull request.
Consensus never reads, writes, executes or merges code.
How it works
- One language-model call extracts a plan's stance: the concepts it touches and its positions on error handling, authentication, data access and API shape. Unaddressed axes stay empty; nothing is guessed.
- The nearest open plans and memory entries are retrieved by vector search.
- Plans are compared deterministically. Shared concept plus disagreeing positions is a clash. Same inputs, same answer, every input logged.
- A hard clash is checked against prior rulings before any human is asked.
Full detail: How it works.
Connecting an agent
Consensus is an MCP server. Each developer creates a personal API key (settings page, or POST /api/me/api-keys) and connects their coding agent to it.
Claude Code, with the guardrail (recommended). The plugin adds the server, a skill that teaches the workflow, and a hook that refuses Edit/Write until the plan is declared and the verdict allows it:
Claude Code, server only:
Cursor, Windsurf, any MCP client. Add to the client's MCP config:
Listed in the MCP Registry as io.github.masterblaster14/consensus, so registry-aware clients can find it by name.
Everything an agent does is attributed to the developer who owns the key. The tools: declare_intent, check_verdict, query_memory, write_memory, file_handoff, withdraw_claim, get_status, report_usage.
Teams and integrations
- Sign in with GitHub or an email link. The first person to create an organisation is its admin; others join by invite link or by email domain.
- One shared live board per repository.
- GitHub: handoffs open pull requests, rulings become PR comments, merged PRs retire their plans.
- Notion: tasks sync in, decisions and rulings mirror out.
Hosted instance: https://consensus-production-aed6.up.railway.app (API docs at /docs, live board at /board).
Running it
Python 3.11, PostgreSQL with pgvector, Redis. Docker Compose for the databases. Offline mode needs no API keys.
Or the whole stack in containers: docker compose --profile full up -d --build.
Setup details, configuration and the full API: Backend reference. Hosting it: Deploying (Render blueprint, Railway, Fly, or any Docker host).
License
MIT. See LICENSE.
Documentation
Source: README.md at commit 94d9bcd
Tools
0Version history
1- v0.1.0LatestSep 16, 2026
Score
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listedRequired15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
