EverOS Distributed Agent Kernel & Process Supervisor

@ever-os/kernel · v3.0.2

A UNIX-like virtual process manager and distributed scheduling substrate for DeepSeek Harness. Delivers POSIX pipes, shared-memory IPC, process isolation, and dynamic cgroups.

Virtual-OSProcess-SupervisorIPC-PipesCgroups
GitHub Stars
41 K+
+12.4% this month
Monthly Downloads
179 K+
Monthly registry pulls
Reach Score
98.8/ 100
Top Tier Ecosystem
Runtime
Cordis v3+
Node 18+ / Bun / Deno

Installation & Integration

CLI one-click launch, package managers, and Cordis integration

bash
manager:
$ pnpm add @ever-os/kernel

Architecture

EverOS applies time-tested UNIX OS principles to large-scale agent orchestration. When dozens of autonomous workers execute simultaneously, naive async loops suffer from deadlocks, memory bloat, and uncontrolled thrashing. This plugin implements a virtual process scheduler atop the Cordis bus. Every task operates as an isolated process with its own PID, virtual file descriptors, and UNIX pipes. Process-level cgroups strictly govern token allocations and wall-clock execution limits, bringing rock-solid determinism to swarm deployments.

Architectural Principles & Constraints

01
Strict Type Isolation

Guaranteed by TypeScript compile-time contracts, inter-plugin event bus calls enjoy zero-drift safety.

02
Sub-Millisecond Hot Reload

Supports dynamic runtime mounting and graceful unloading without restarting the primary host process.

03
Deterministic State Machine

Embeds multi-phase execution lifecycle guards, preventing context loss during long-horizon reasoning.

04
Zero Native Build Dependencies

Designed for lightweight cross-platform environments, booting instantly across Node.js, Bun, and Deno.

Core Features

01
UNIX-Style Process Abstraction: Provides discrete PIDs, file descriptors, and standard stream I/O
02
Inter-Agent Data Pipelining: Compose agents seamlessly using familiar `agentA | agentB` workflows
03
Token-Level Cgroups Enforcement: Caps maximum token and compute burn per process strictly
04
Automated Zombie Reaper: Cleans dangling child processes and ephemeral temp artifacts permanently

Core Workflow

01

Process Fork & Spawning

Forks an isolated process container with unique PID, env vars, and working dir.

02

POSIX Pipe Chaining

Binds stdin/stdout pipes, enabling frictionless streaming between agent workers.

03

Resource Quota Enforcement

Enforces cgroup constraints on memory usage, concurrency, and token burn.

04

Signal Handling & Reaper

Dispatches SIGTERM/SIGKILL to manage uncooperative tasks and reaps zombie handles.

Configuration Parameters Reference (YAML / JSON)

ParameterTypeDefaultDescription
maxProcessCountnumber64Maximum concurrent virtual processes allowed
defaultTokenLimitnumber50000Default token burn limit per process instance
enableIPCbooleantrueEnable inter-process pipe communication

Use Cases

Enterprise Production Agent

Relies on microkernel lifecycle guards and fault-tolerant state machines for continuous reliability.

SWE-bench Benchmark Evaluation

Native integration with SWE-bench workflows, automatically capturing diffs and verification metrics.

Autonomous Code Refactoring

Separates reasoning from tool actions to independently locate and refactor multi-file codebases.

Cross-Tool Workflow Automation

Safely orchestrates events across sandboxes to seamlessly link enterprise developer tooling.

Best Practices

01
Sandbox Permission Guard

Strictly isolate sub-process calls and network scope; deploy within Docker containers in production.

02
Exponential Backoff Retries

Configure adaptive exponential retries with strict timeouts to mitigate upstream model rate limits.

03
Session State Checkpointing

Persist state machine snapshots to survive hardware interruptions and resume instantly without loss.

04
Full Trajectory Audit Logs

Enable full trace logging, aggregating reasoning thought streams and tool I/O into your observability hub.

FAQ

Q1:How to handle timeouts in long-running autonomous tasks?

Increase the timeout parameter inside your YAML configuration and dispatch periodic heartbeat signals across the Cordis event bus. For long-running tool execution and model reasoning, configure persistent session snapshotting so suspended tasks can safely resume their exact context after interruptions, preventing the kernel from recycling active agent sessions prematurely.

Q2:How to capture and stream the model reasoning thought process?

The harness runtime natively provides end-to-end streaming hooks while its state machine automatically intercepts and strips <think> reasoning tags from model responses. Subscribe directly to the onThink event listener to consume live reasoning token streams in real-time, delivering typewriter animation to the user interface while persisting full trajectories for audit compliance.

Q3:How to resolve dependency conflicts across multiple plugins?

Cordis microkernel uses directed acyclic graph topological sorting to dynamically resolve plugin dependencies. When shared services or runtime versions conflict, assign distinct isolated namespaces at the application entrypoint. Leveraging context injection alongside lazy activation ensures dependencies load strictly on-demand when tools are triggered, maintaining system stability and preventing memory bloat.

Q4:How to enforce permissions and sandbox isolation in production?

Combine isolated container sandboxing with fine-grained capability checks to prevent plugins from accessing sensitive files or unauthorized external networks. Enforce explicit runtime system call whitelisting through the microkernel, executing all third-party tool scripts inside isolated ephemeral containers to block arbitrary code execution and eliminate security privilege escalation risks entirely.

Recommended Ecosystem Plugins

Explore related Cordis extensions designed to work synergistically