A high-performance MCP agent mail server built in Rust. Named in honor of Eric Allman, creator of Sendmail.
Allman acts as the communication backbone for large swarms of autonomous AI agents — concurrent durable message routing, near-real-time search, and a Git-backed profile audit trail, all exposed through the Model Context Protocol.
[ Agent Swarm ] [ vLLM / GPU Inference ]
| (Port 8001)
MCP JSON-RPC |
v |
+----------------------------------------------+
| ALLMAN SERVER (Rust) |
| |
| MCP Controller (tools/call, tools/list) |
| | |
| PostOffice |
| ├─ DashMap recoverable hot projection|
| ├─ Fjall durable message log |
| ├─ Tantivy NRT full-text search |
| └─ Git Actor profile audit trail |
| |
| Persist Worker batched indexing pipeline |
| crossbeam-channel → Tantivy IndexWriter |
+----------------------------------------------+
Port 8000
Hot path: validation and reads remain in memory. Message writes pass through a dedicated Fjall group-commit actor and are acknowledged only after the configured durability boundary.
Persistence: canonical messages and per-recipient delivery pointers are stored atomically. DashMap inboxes and the Tantivy index are rebuildable projections. A 350µs microbatch window amortizes sync cost across concurrent sends.
Connect any MCP-compatible client to http://localhost:8000/mcp.
| Tool | Description |
|---|---|
create_agent |
Register an agent (project_key, name_hint, program, model) |
send_message |
Send a message (from_agent, to, subject, body, project_id) |
get_inbox |
Retrieve and drain unread messages for an agent |
receive_messages |
Lease unread messages with a visibility timeout |
ack_messages |
Durably acknowledge a leased batch |
search_messages |
Full-text search across all indexed messages |
- Rust 1.90+
- Docker (optional — for containerized deployment and vLLM)
- NVIDIA GPU +
nvidia-container-toolkit(optional — only for LLM inference)
git clone https://github.com/copyleftdev/allman.git
cd allman
cargo build --release# Start the server (binds to 0.0.0.0:8000)
cargo run --releaseConfiguration via environment variables (or .env):
| Variable | Default | Description |
|---|---|---|
INDEX_PATH |
allman_index |
Tantivy index directory |
REPO_ROOT |
allman_repo |
Git audit trail directory |
STORE_PATH |
allman_store |
Fjall durable message store directory |
DURABILITY_MODE |
strict |
strict, balanced, or buffered |
SERVER_ADDR |
0.0.0.0:8000 |
HTTP listen address |
RUST_LOG |
allman=debug |
Log level filter |
strict uses fsync, balanced uses fdatasync, and buffered protects against process crashes but not OS or power loss. Production deployments should use strict unless their filesystem guarantees make balanced appropriate.
# Allman server only docker compose up allman -d # Allman + vLLM GPU inference sudo ./setup_gpu.sh # one-time NVIDIA toolkit install docker compose up -d
Included binaries demonstrate swarm behavior with LLM-driven agents:
| Binary | Description |
|---|---|
cyber_sim |
30-agent cybersecurity incident response (Blue Team, Forensics, CISO) |
black_friday |
Retail chaos simulation with personality-driven personas |
escrow_sim |
Real estate closing day with buyer, seller, and escrow officer |
swarm_stress |
High-concurrency stress test for throughput benchmarking |
benchmark |
Targeted latency and throughput measurements |
cargo run --release --bin cyber_sim cargo run --release --bin swarm_stress
Note: Simulations that use LLM inference require a running vLLM instance on port 8001. The stress test and benchmark run against Allman alone.
src/
├── main.rs Axum server, routing, MCP endpoint
├── controllers.rs MCP tool dispatch (create_agent, send_message, etc.)
├── durable.rs Fjall group-commit actor, recovery, leases, acknowledgements
├── state.rs PostOffice: DashMap state, Tantivy index, persist pipeline
├── models.rs Data types (InboxEntry, Agent, Message)
├── git_actor.rs Dedicated OS thread for Git audit commits
└── bin/
├── benchmark.rs
├── black_friday.rs
├── cyber_sim.rs
├── escrow_sim.rs
├── simulation.rs
└── swarm_stress.rs
cargo fmt cargo check # must pass clean cargo test
MIT