car-runtime 0.42.0

Common Agent Runtime — Python bindings for deterministic AI agent execution

car-runtime (Python)

Python bindings for Common Agent Runtime (CAR) — a deterministic execution layer for AI agents. Models propose; the runtime validates and executes.

As of v0.8, this package is a thin daemon client: every method proxies to a singleton car-server daemon over WebSocket. Inference, the per-session memory graph, and tool dispatch all live on the daemon side. Start car-server once per host before using the bindings (car-server ships in the same wheel; see "Start the daemon" below).

Pre-built wheels (abi3, Python 3.9+) for:

• macosx_15_0_arm64 — macOS 15+ on Apple Silicon (Intel Macs dropped — see CHANGELOG)
• manylinux_2_17_x86_64, manylinux_2_28_aarch64

Building from source on macOS: set MACOSX_DEPLOYMENT_TARGET=15.0 when invoking maturin build. MLX's bundled Metal shaders don't compile against the default 11.0 target, and our release wheels target 15.0 because the compiled extension pulls in libc++ symbols (notably std::exception_ptr::__from_native_exception_pointer) that only exist on macOS 15+. A lower target produces a wheel whose tag doesn't match what the binary actually requires at dlopen time.

Install

From a release wheel (substitute the current version for X.Y.Z):

pip install https://github.com/Parslee-ai/car/releases/download/vX.Y.Z/car_runtime-X.Y.Z-cp39-abi3-macosx_15_0_arm64.whl

Or build from source:

pip install maturin
cd car-rs/crates/car-ffi-pyo3
maturin develop --release

The import name is car_runtime (matching the PyPI package name).

Start the daemon

# The car-server binary ships inside the wheel. Default port 9100;
# auth on by default. Foreground (Ctrl-C to stop):
python -m car_runtime.server

# Or background:
python -m car_runtime.server &

# Override the URL the bindings use:
export CAR_DAEMON_URL=ws://127.0.0.1:9100

On macOS the SwiftUI menubar host (CAR Host.app) launches the daemon for you. Install it once from the .pkg installer on the latest GitHub release; from then on it supervises car-server and keeps itself up to date via Sparkle.

Quickstart

import json
from car_runtime import CarRuntime, verify

rt = CarRuntime()   # lazy-connects to ws://127.0.0.1:9100/

# Tools + policies — proxied to the daemon's per-session runtime
# and persist for the lifetime of this CarRuntime's WS connection.
rt.register_tool("shell")
rt.register_policy(
    "no_rm",
    "deny_tool_param",
    target="shell",
    key="command",
    pattern="rm -rf",
)

# Ground with facts (proxied to the daemon's per-session memgine).
rt.add_fact("project_language", "Python", "pattern")

# Static verification — runs on the daemon side, no model needed.
proposal = json.dumps({
    "actions": [{
        "id": "a1",
        "type": "tool_call",
        "tool": "shell",
        "parameters": {"command": "ls"},
        "dependencies": [],
    }],
})

check = json.loads(rt.verify_proposal(proposal))
if not check["valid"]:
    raise RuntimeError(f"invalid proposal: {check['issues']}")

# Proposal execution with a Python tool callback is not exposed on
# the PyO3 surface in v0.8 — connect to the daemon's WebSocket
# directly with `websockets` (or any WS library) and use:
#   - `proposal.submit` (your client → daemon)
#   - a `tools.execute` handler on the same connection (daemon → you)
# See docs/websocket-protocol.md and
# car-rs/examples/ws-client-python/ for a working sketch.

Streaming inference

Streaming is WebSocket-only. Connect to car-server, call the infer_stream JSON-RPC method, and consume inference.stream.event notifications. CarRuntime.infer_stream remains only as an ABI-compatibility stub; it always raises RuntimeError and never invokes its callback. See the streaming cookbook.

Multi-agent coordination

import json
from car_runtime import register_agent_runner, run_swarm

def agent_fn(spec_json: str, task: str) -> str:
    spec = json.loads(spec_json)
    # Call your LLM of choice, returning an AgentOutput JSON.
    return json.dumps({"name": spec["name"], "response": "...", "tool_calls": []})

# Option A: register once, then call run_* without passing agent_fn each time.
register_agent_runner(agent_fn)
result = run_swarm(
    "parallel",
    json.dumps([
        {"name": "researcher", "role": "gather facts", "model": "gpt-5"},
        {"name": "writer",     "role": "compose summary", "model": "claude-opus-4-7"},
    ]),
    "summarize the CAR paper",
)

# Option B: pass agent_fn per call.
result = run_swarm("parallel", agents_json, task, agent_fn=agent_fn)

API surface

The runtime (CarRuntime) exposes:

• State: state_set, state_get, state_exists, state_snapshot, state_keys
• Memory: add_fact, query_facts, fact_count, build_context, build_context_fast, persist_memory, load_memory, consolidate
• Skills: ingest_skill, find_skill, report_outcome, distill_skills, ingest_distilled_skills, list_skills, domains_needing_evolution, repair_skill, evolve_skills
• Tools + policies: register_tool, register_agent_basics, register_policy, set_replan_config
• Inference: infer, infer_tracked, infer_tracked_with_request (request-shaped GenerateRequest, including params.strict_model), infer_with_context, infer_with_context_tracked, embed, rerank, classify, prepare_speech_runtime, transcribe, synthesize
• Models: list_models, pull_model, remove_model, list_models_unified, register_model, route_model, model_stats
• Execution: event_count, verify_proposal, execute_proposal

Module-level standalone functions:

• Verification: verify, simulate, optimize, equivalent
• Stateless execute: execute (creates a fresh Runtime; for long-lived use, prefer CarRuntime.execute_proposal)
• Multi-agent: register_agent_runner, run_swarm, run_pipeline, run_supervisor, run_map_reduce, run_vote
• Scheduler: create_task, run_task, run_task_loop, ensure_dream_task
• Planner: rank_proposals

Compatibility-only method: infer_stream (always raises; use WebSocket).

Structured returns are JSON-encoded strings — json.loads them on the Python side. This keeps the FFI surface stable across binding and protocol changes.

Type stubs

The wheel ships car_runtime.pyi alongside the compiled extension and a py.typed marker (PEP 561). mypy, pyright, Pylance, and similar tools pick up the full method signatures, parameter docstrings, and return-shape descriptions automatically — no extra install needed.

If you're editing the source tree (not the published wheel), the same files live at crates/car-ffi-pyo3/car_runtime.pyi and must be kept in sync with src/lib.rs. See CLAUDE.md for the FFI-bindings parity rule.

Development

# Install dev deps.
pip install maturin pytest

# Build and install in editable mode.
cd car-rs/crates/car-ffi-pyo3
maturin develop

# Run the smoke tests.
pytest tests/ -v

Architecture

This package is a thin PyO3 client to the singleton car-server daemon over WebSocket — CarRuntime() lazy-connects, every method proxies through the JSON-RPC dispatcher, and the daemon owns inference / memory / tool dispatch / per-session state.

Pre-v0.8 (the RuntimeMode::Embedded path) the wheel hosted an in-process car-engine + car-memgine and ran inference under py.allow_threads(...). That path was retired to close the multi-tenant overcommit hazard CAR-issue #139 was opened for — two FFI consumers in different processes each spawned a fresh admission semaphore + model cache, and concurrent runs could overwhelm the host. v0.8 takes the harder path: one daemon per host, every client attaches.

See the repo README for the broader CAR architecture and docs/proposals/daemon-as-default-runtime.md for the v0.8 rationale.

License

Free for any use including commercial; free to redistribute unmodified. Modification, reverse engineering, and derivative works are not permitted. See LICENSE for the full text. Copyright © 2026 Parslee AI.