gianlucamazza/orka
A modular agent orchestration platform built in Rust — multi-channel messaging, priority queues, LLM integration, skill system, MCP/A2A protocols, and sandboxed execution.
Platform-specific configuration:
{
"mcpServers": {
"orka": {
"command": "npx",
"args": [
"-y",
"orka"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
[](https://github.com/gianlucamazza/orka/actions/workflows/ci.yml) [](LICENSE-MIT) [](LICENSE-APACHE) [](https://www.rust-lang.org)
A self-learning AI agent orchestration platform built in Rust.
Orka routes messages from Telegram, Discord, Slack, WhatsApp, and HTTP through a priority queue to LLM-powered agents. Agents execute tools, build knowledge via RAG, learn from experience, and coordinate through multi-agent graphs — extensible with WASM plugins and MCP/A2A protocols.
<p align="center"> </p>
<details> <summary>More demos</summary>
<p align="center"> </p>
<p align="center"> </p>
<p align="center"> </p>
</details>
flowchart TD
Clients["External Clients<br/>Telegram · Discord · Slack · WhatsApp · HTTP"]
Auth["Auth Middleware<br/>orka-auth · API Key · JWT"]
Adapters["Adapters<br/>Platform → Envelope conversion"]
Bus["Message Bus<br/>Redis Streams"]
GW["Gateway<br/>Dedup · Rate-limit · Session · Priority routing"]
PQ["Priority Queue<br/>Redis Sorted Set<br/>Urgent > Normal > Background → DLQ"]
Workers["Worker Pool (N concurrent)"]
A2A["A2A Protocol<br/>orka-a2a · Agent card · JSON-RPC"]
Eval["Eval Service<br/>orka-eval · Skill scenario testing"]
subgraph Agent["Agent — GraphExecutor"]
direction TB
subgraph Context["Loading reviews...