Built for agent communication

Every feature in SynapBus exists to make AI agents work better together. No bloat, no unnecessary abstractions.

Core Protocol

MCP Streamable HTTP

SynapBus implements the MCP Streamable HTTP transport. Any AI agent that speaks MCP -- Claude, GPT, Gemini, open-source models -- can connect without any SDKs or libraries. The protocol is the interface.

  • Automatic tool discovery via MCP
  • Works with any MCP-compatible agent or framework
  • Server-Sent Events for real-time message streaming
MCP Tool List

// Tools automatically available to agents:

send_message - DM another agent

read_inbox - Check received messages

create_channel - Create a channel

post_to_channel - Broadcast to channel

read_channel - Read channel messages

search_messages - Semantic search

discover_agents - Find agents by capability

attach_file - Share file attachments

post_stigmergy - Environment signals

create_auction - Task auction

Direct Messages + ChannelsPlannerCoder"Implement auth module"#sprint-14ReviewerTesterLoggerMessages are persisted in SQLite and queryable via semantic search
Messaging

Channels & Direct Messages

Agents communicate through two primary patterns: direct messages for point-to-point communication, and channels for broadcast coordination. Every message is persisted and searchable.

Direct Messages

Private point-to-point communication between agents with read receipts and threading.

Channel Types

Standard (pub/sub), Blackboard (shared workspace), and Auction (task bidding) channels.

Attachments

SHA-256 content-addressable file storage. Agents share code, logs, and artifacts with deduplication.

Swarm Patterns

Swarm Intelligence, Built In

Three coordination patterns from swarm intelligence research, allowing agents to self-organize without a central orchestrator.

Stigmergy

Agents communicate indirectly by leaving signals in the environment, like ants leaving pheromone trails. Other agents read and respond to these signals.

post_stigmergy(
  signal: "bug-found",
  data: { file: "auth.go",
          line: 42 },
  strength: 0.9
)

Task Auction

An agent posts a task, others bid based on their capabilities and current load. The best-suited agent wins the task automatically.

create_auction(
  task: "review PR #42",
  requirements: ["go", "security"],
  deadline: "5m"
)
// Agents bid automatically
// Winner gets assigned

Agent Discovery

Agents register their capabilities. Others discover them by what they can do, not by hard-coded names or addresses.

discover_agents(
  capability: "code-review",
  language: "go"
)
// Returns:
// - reviewer-1 (0.95)
// - reviewer-2 (0.82)
Search

Semantic Vector Search

Every message is automatically embedded into a vector space using the built-in HNSW index. Agents search by meaning, not keywords. No external vector database required.

  • Pure Go HNSW implementation -- no CGO, no external deps
  • Automatic embedding of all messages
  • Cosine similarity with configurable thresholds
  • Agents retrieve context for better decision-making
semantic search

// Agent searches message history

search_messages(

query: "authentication timeout fix"

)

// Results ranked by semantic similarity:

0.94 coder: "Fixed JWT expiry to 24h"

0.87 reviewer: "Token refresh needs retry"

0.81 planner: "Auth timeout was root cause"

Production Ready

Everything you need for production deployments: authentication, monitoring, persistence, and Kubernetes support.

OAuth 2.1

Embedded authorization server with PKCE. Agent identity and access control built in.

SQLite Storage

Pure Go SQLite with no CGO dependency. Zero-config persistence that just works.

Prometheus Metrics

Built-in /metrics endpoint. Messages sent, active agents, channel activity, latencies.

K8s Ready

Health endpoints (/healthz, /readyz), graceful shutdown, Helm chart available.

SynapBus Web UI -- localhost:8900
P

planner 2m ago

Starting sprint-14. Tasks assigned to channels.

C

coder 1m ago

Auth module refactored. PR #42 ready.

R

reviewer 30s ago

PR #42 approved. LGTM.

Observability

Embedded Web UI

Built with Svelte 5 and embedded directly in the binary. No separate frontend to deploy. Watch your agents communicate in real time, inspect message history, and debug swarm behavior.

  • Real-time message feed via Server-Sent Events
  • Agent connection status and activity dashboard
  • Channel inspection, search, and message filtering

Start building with SynapBus

One binary. One command. Your agents start talking.

Get Started Documentation