Magy Platform

Engineering leadership, architecture decisions, cross-agent coordination

Project coordination, status tracking, prioritization

System design, code implementation, task decomposition

Code implementation, file operations, git workflows

Code implementation, debugging, feature development

Testing, validation, quality assurance

Infrastructure, deployment, monitoring

Short-term, per-task context. Fast in-memory store cleared after task completion.

Historical records of past interactions and task outcomes. Postgres-backed with timestamps.

Vector embeddings for similarity search. pgvector with HNSW indexing for sub-50ms retrieval.

Learned patterns and procedures. How-to knowledge extracted from successful task completions.

Standard

File access scoped to workspace, full network, shell allowed with confirmation.

Strict

Workspace-scoped files, network restricted to allowlist, no shell without explicit approval.

Isolated

Temp-dir only, no network, no shell. For untrusted marketplace skills and WASM plugins.

Skill System

Skills are composable, agent-invocable capabilities defined as YAML with embedded instructions. They can be bundled with the runtime or loaded from the marketplace. WASM skills execute in sandboxed Wasmtime environments.

# skills/code-review.yaml
name: code-review
description: "Review code changes"
tools: [git, filesystem]
steps:
  - action: git_diff
  - action: analyze
    prompt: "Review these changes..."
  - action: respond

Plugin System

Plugins extend the runtime with custom tools, connectors, and event handlers. They implement the Plugin trait and are registered at startup. Hot-reload supported for development.

#[async_trait]
pub trait Plugin: Send + Sync + 'static {
    fn name(&self) -> &str;
    async fn init(&self, ctx: &PluginContext) -> Result<()>;
    fn tools(&self) -> Vec<Box<dyn Tool>>;
    async fn shutdown(&self) -> Result<()>;
}

WebSocket Protocol

// Client → Server
{ "type": "subscribe", "agent_id": "aria" }
{ "type": "send_message", "agent_id": "aria", "content": "..." }
{ "type": "ping" }

// Server → Client
{ "type": "agent_message", "agent_id": "aria", "content": "..." }
{ "type": "agent_stream", "chunk": "...", "seq": 1, "done": false }
{ "type": "status_update", "agents": [...] }

SSE Events

// Event types:
event: connected
data: {"session_id": "..."}

event: message:new
data: {"agent_id": "aria", "content": "..."}

event: agent:stream
data: {"agent_id": "aria", "chunk": "...", "seq": 1}

event: agent:status
data: {"id": "aria", "status": "running"}

[magy]
name = "my-project"
description = "Multi-agent orchestration"

[[provider]]
name = "anthropic"
api_key_env = "ANTHROPIC_API_KEY"
models = ["claude-sonnet-4-20250514", "claude-haiku-4-5-20251001"]

[infrastructure]
nats_url = "nats://localhost:4222"
postgres_url = "postgresql://localhost/magy"
redis_url = "redis://localhost:6379"
api_port = 3011

[[agent]]
id = "aria"
name = "Aria"
model = "claude-sonnet-4-20250514"
system_prompt = "prompts/architect.md"
tools = ["filesystem", "shell", "git", "github"]
budget_cents_per_hour = 500

[channels]
telegram_enabled = true
telegram_token_env = "TELEGRAM_BOT_TOKEN"
telegram_default_agent = "aria"

[[guardrail]]
tool = "shell"
action = "block"
pattern = "rm -rf /"
message = "Dangerous command blocked"

[agent.personality]
traits = ["methodical", "detail-oriented"]
risk_tolerance = 0.3
collaboration_style = "lead"
verbosity = "concise"

[scheduling]
poll_interval_secs = 30
max_concurrent = 10

[[cron]]
id = "daily-standup"
schedule = "0 0 9 * * *"
agent = "aria"
task = "Run daily standup"

[infrastructure.health]
check_interval_secs = 30
error_threshold = 5
restart_on_failure = true

Assesses how demanding each task is and routes it to the cheapest capable model automatically — no manual model selection, and no paying frontier prices for simple turns.

Shared persistent knowledge that agents learn from each other. What gets reinforced sticks; what goes stale fades out of context on its own.

Work an agent is likely to need is started early, so when the response arrives the result is already waiting instead of costing another round-trip.

Third-party skills execute in Wasmtime sandboxes with configurable resource limits. Marketplace skills can't escape their sandbox. Hot-reload without restarting the runtime.

MagyVerse: a voxel-based 3D world (Three.js + R3F) where agents are visible characters. Watch agents collaborate, see their thought processes, interact via chat — all in real-time via WebSocket.

Tool execution overlaps with generation instead of waiting for the model to finish speaking, which takes several seconds out of every round.

Policy-as-config safety rules defined in magy.toml. Block dangerous commands, flag sensitive operations for approval, enforce token limits — all without writing code. Regex patterns compiled at startup for zero runtime overhead.