Neutral control plane for coding-agent fleets: claims, roles, mailbox reliability, receipts, audit, federation, dead-letter visibility, sandbox receipts, and cross-agent coordination. This is still pre-1.0.0 - Software works however you might need help from your local agents to set it up.
- ✓Open-source license (AGPL-3.0)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
git clone https://github.com/anulum/synapse-channel && cp synapse-channel/*.md ~/.claude/agents/Resumen de Subagents
<!--
SPDX-License-Identifier: AGPL-3.0-or-later
Commercial license available
© Concepts 1996–2026 Miroslav Šotek. All rights reserved.
© Code 2020–2026 Miroslav Šotek. All rights reserved.
ORCID: 0009-0009-3560-0851
Contact: www.anulum.li | protoscience@anulum.li
mcp-name: io.github.anulum/synapse-channel
SYNAPSE CHANNEL — repository overview
-->
<p align="center">
<img src="https://raw.githubusercontent.com/anulum/synapse-channel/main/docs/assets/header.png" width="1280" alt="SYNAPSE CHANNEL — local-first multi-agent coordination bus">
</p>
<p align="center">
<strong>The local-first coordination bus for fleets of AI agents.</strong><br>
One WebSocket hub is the shared source of truth for presence, file-scope claims, a shared plan, task status, and capabilities — for agents working in one repository or across a whole ecosystem of them.
</p>
<p align="center">
<em>Flagship example:</em> coordinate parallel AI coding agents through declared file scopes — the hub refuses a second overlapping live claim, while covered provider hooks and the staged Git gate enforce only their documented mutation boundaries.
</p>
<p align="center">
<a href="https://github.com/anulum/synapse-channel/actions/workflows/ci.yml"><img src="https://github.com/anulum/synapse-channel/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
<a href="https://github.com/anulum/synapse-channel/actions/workflows/fuzz.yml"><img src="https://github.com/anulum/synapse-channel/actions/workflows/fuzz.yml/badge.svg" alt="Fuzz"></a>
<a href="https://github.com/anulum/synapse-channel/actions/workflows/link-check.yml"><img src="https://github.com/anulum/synapse-channel/actions/workflows/link-check.yml/badge.svg" alt="Link check"></a>
<a href="https://github.com/anulum/synapse-channel/actions/workflows/clients-cockpit.yml"><img src="https://github.com/anulum/synapse-channel/actions/workflows/clients-cockpit.yml/badge.svg" alt="Cockpit CI"></a>
<a href="https://github.com/anulum/synapse-channel/actions/workflows/codeql.yml"><img src="https://github.com/anulum/synapse-channel/actions/workflows/codeql.yml/badge.svg" alt="CodeQL"></a>
<a href="https://pypi.org/project/synapse-channel/"><img src="https://img.shields.io/pypi/v/synapse-channel" alt="PyPI version"></a>
<a href="https://pypi.org/project/synapse-channel/"><img src="https://img.shields.io/pypi/dm/synapse-channel" alt="PyPI downloads"></a>
<a href="https://pepy.tech/project/synapse-channel"><img src="https://static.pepy.tech/badge/synapse-channel" alt="Total downloads"></a>
<a href="https://github.com/sponsors/anulum"><img src="https://img.shields.io/badge/GitHub-Sponsors-ea4aaa?logo=githubsponsors" alt="Sponsor SYNAPSE CHANNEL on GitHub"></a>
<a href="LICENSE"><img src="https://img.shields.io/badge/License-AGPL%20v3-blue.svg" alt="License: AGPL v3"></a>
<a href="https://www.remanentia.com/synapse/pricing.html"><img src="https://img.shields.io/badge/commercial%20licence-available-0a7d3c" alt="Commercial licence available"></a>
<img src="https://img.shields.io/badge/python-3.10%2B-blue" alt="Python 3.10+">
<a href="https://codecov.io/gh/anulum/synapse-channel"><img src="https://codecov.io/gh/anulum/synapse-channel/branch/main/graph/badge.svg" alt="Coverage"></a>
<a href="https://api.reuse.software/info/github.com/anulum/synapse-channel"><img src="https://api.reuse.software/badge/github.com/anulum/synapse-channel" alt="REUSE status"></a>
<a href="https://www.bestpractices.dev/projects/13565"><img src="https://www.bestpractices.dev/projects/13565/badge" alt="OpenSSF Best Practices: Passing"></a>
<a href="https://securityscorecards.dev/viewer/?uri=github.com/anulum/synapse-channel"><img src="https://api.securityscorecards.dev/projects/github.com/anulum/synapse-channel/badge" alt="OpenSSF Scorecard"></a>
<a href="https://github.com/astral-sh/ruff"><img src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json" alt="Ruff"></a>
<a href="https://doi.org/10.5281/zenodo.20801559"><img src="https://zenodo.org/badge/DOI/10.5281/zenodo.20801559.svg" alt="DOI"></a>
</p>
<p align="center">
<strong>English</strong> ·
<a href="docs/readme/README.zh-CN.md">简体中文</a> ·
<a href="docs/readme/README.es.md">Español</a> ·
<a href="docs/readme/README.pt-BR.md">Português (Brasil)</a> ·
<a href="docs/readme/README.ja.md">日本語</a> ·
<a href="docs/readme/README.ko.md">한국어</a> ·
<a href="docs/readme/README.de.md">Deutsch</a> ·
<a href="docs/readme/README.fr.md">Français</a> ·
<a href="docs/readme/README.sk.md">Slovenčina</a>
</p>
A local-first coordination bus for a fleet of AI agents working in parallel —
within a single repository or spread across a whole ecosystem of them. One
WebSocket hub is the shared source of truth for **presence**, **work claims**,
**chat**, **task status**, and **resource offers**: agents address each other
across projects and share one plan, while file-scope claims keep the agents in any
one repository from receiving overlapping live authority. Documented provider
hooks and the staged Git gate enforce that authority only on their covered
mutation surfaces.
### Watch the presentation
[](https://www.youtube.com/watch?v=Dlyn7k0M_Xs)
[Watch the SYNAPSE CHANNEL presentation on YouTube](https://www.youtube.com/watch?v=Dlyn7k0M_Xs) (8 minutes; starts from the beginning).
> **New here?** Read [**Why SYNAPSE CHANNEL**](docs/why-synapse.md) — a
> five-minute read on what it is, what you build on it, how it differs from the
> tools next to it, and why coordination becomes the bottleneck once you run more
> than one agent.
> **Project lineage:** SYNAPSE CHANNEL dates back to **September 2025**.
The bus is transport-light (one dependency, `websockets`), hub-centric by design
(one place owns presence, leases, and history), and runs entirely on the local
machine. Model workers reply on-channel through any OpenAI-compatible endpoint,
including a local Ollama server, with a deterministic rule-based fallback for
offline use.
**Your existing agents plug in without new code.** Any Model Context Protocol
host — Claude Code, Claude Desktop, Cursor — reaches the bus through the bundled
`synapse mcp` server, which exposes send, durable inbox, status, claim, release,
handoff, and task verbs as MCP tools plus the board, agents, and resources as
read-only MCP resources. Agents that speak A2A connect through the Agent Card face instead.
The hub itself stays protocol-agnostic and the core install keeps its single
dependency — the MCP and A2A adapters are optional extras (`pip install
'synapse-channel[mcp]'`). See the [MCP guide](docs/mcp.md).
```bash
python -m pip install synapse-channel && synapse demo
```
<p align="center">
<a href="https://pypi.org/project/synapse-channel/"><strong>Get the Python package</strong></a>
·
<a href="#first-60-seconds">Run the first 60 seconds</a>
·
<a href="docs/quickstart.md">Read the quickstart</a>
</p>
## Coordinate. Observe. Govern.
Synapse's daily promise is three explicit loops:
- **Coordinate** declared work and surface collisions: `synapse git-init`, `synapse git-claim`,
`synapse git-claim-check --staged`, `synapse task`, and `syn ack` turn work
scope, dependencies, and evidence into shared state instead of side-channel
notes.
- **Observe** the fleet from durable state: `synapse who`, `synapse state`,
`synapse dashboard`, `synapse event-query`, and observed peer rows show who is
present, what is claimed, what changed, and which peer-hub facts are advisory.
- **Govern** risky actions with evidence: policy checks, approvals, release
receipts, Merkle roots, ACL surfaces, federation, and encryption-key commands
make operator decisions auditable. Governance surfaces report by default;
operators decide what blocks a merge, release, or cross-hub action.
- **Protect the durable log at rest** with optional **SQLCipher** page encryption
for the live hub event store (plus whole-file AES-GCM envelopes for relay
logs, A2A state, cursors, and archives). See
[SQLCipher live event store](#sqlcipher-live-event-store-at-rest) below.
## What it does, surface by surface
Seven shipped coordination surfaces, each named by the command or doc that
delivers it today:
- **Claim before edit.** [`synapse git-init`](#git-native-claims) installs claim-aware Git hooks; `synapse git-claim` records an exact worktree, branch, and path scope so an overlapping claim can be refused before files diverge.
<p align="center">
<img src="docs/assets/feature-claim-conflict.png" width="809" alt="A live Synapse claim owner and a competing overlapping claim refused before editing begins">
</p>
- **Block unclaimed native file edits.** [Provider file-edit claim hooks](docs/claim-guard-hooks.md) adapt Claude Code `Edit|Write`, Codex `apply_patch`, Gemini CLI `replace|write_file`, and Kimi `Edit|Write` to one live-claim decision engine.
<p align="center">
<img src="docs/assets/feature-edit-denial.png" width="809" alt="A provider edit hook denying a native file edit because the seat holds no matching claim">
</p>
- **Share the plan.** `synapse task` and [`synapse board`](docs/coordination-model.md) keep task state, dependencies, and ready work on the hub instead of in separate agent notes.
<p align="center">
<img src="docs/assets/demo.gif" width="845" alt="A Synapse task board changing a dependent task from blocked to ready after its prerequisite completes">
</p>
- **Hand work over without an ownership gap.** [Atomic handoff](docs/coordination-model.md#4-hand-off-and-recover) moves the held task, scope, status, and checkpoint to an online recipient without a release-and-reclaim window.
<p align="center">
<img src="docs/assets/feature-atomic-handoff.png" width="809" alt="An atomic Synapse handoff moving a held task, scope, staLo que la gente pregunta sobre synapse-channel
¿Qué es anulum/synapse-channel?
+
anulum/synapse-channel es subagents para el ecosistema de Claude AI. Neutral control plane for coding-agent fleets: claims, roles, mailbox reliability, receipts, audit, federation, dead-letter visibility, sandbox receipts, and cross-agent coordination. This is still pre-1.0.0 - Software works however you might need help from your local agents to set it up. Tiene 4 estrellas en GitHub y su última actualización registrada es del 2026-09-23.
¿Cómo se instala synapse-channel?
+
Puedes instalar synapse-channel clonando el repositorio (https://github.com/anulum/synapse-channel) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar anulum/synapse-channel?
+
Nuestro agente de seguridad ha analizado anulum/synapse-channel y le ha asignado un Trust Score de 95/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene anulum/synapse-channel?
+
anulum/synapse-channel es mantenido por anulum. La última actividad registrada en GitHub es del 2026-09-23, con 0 issues abiertos.
¿Hay alternativas a synapse-channel?
+
Sí. En ClaudeWave puedes explorar subagents similares en /categories/agents, ordenados por popularidad o actividad reciente.
Despliega synapse-channel en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/anulum-synapse-channel)<a href="https://claudewave.com/repo/anulum-synapse-channel"><img src="https://claudewave.com/api/badge/anulum-synapse-channel" alt="Featured on ClaudeWave: anulum/synapse-channel" width="320" height="64" /></a>Más Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.