The Codebolt Engine

An advanced agent execution engine. As simple as a coding CLI. As powerful as autonomous company infrastructure.

Codebolt is not an agent — it's the engine that runs agents. Not a framework — it's the execution environment where agents, plugins, and applications operate. Every other tool is one thing. Codebolt is the engine that becomes what you need.

TOPOLOGY

Engine + Channels + Interfaces

Agents connect through the Agent SDK. Plugins extend through the Plugin SDK. Interfaces connect through the Client SDK. All three channels meet at the engine core.

CODEBOLT ENGINE 73 controllers · 134 services stigmergy · drift · narrative deliberation · governance three-tier memory · hostbridge CLIENT SDK PLUGIN SDK PROVIDERS env bridge AGENT SDK IDE electron TUI go / charm CUSTOM UI your build HEADLESS cli / ci WEB browser PLUGIN_CI build / deploy PLUGIN_SLACK messaging PLUGIN_GIT scm / pr PLUGIN_CLOUD storage / fn DOCKER_ENV sandboxed CLOUD_VM gpu · scale REMOTE_HOST ssh · proxy AGENT_01 custom · code AGENT_02 remix · yaml AGENT_03 flow · visual
CONNECTION
PACKET
ENGINE CORE
REMOTE

Engine Architecture

Other tools operate at Layer 1-2. Agent frameworks at Layer 2. Codebolt is all five layers — a complete engine.

Interface Layer — IDE, TUI, CLI, Web surface
Communication Layer — Agent SDK, Plugin SDK, Client SDK runtime
Coordination Layer — Stigmergy, Deliberation, Pheromones coordination
Intelligence Layer — Drift Engine, Narrative Versioning (Rust) intelligence
Infrastructure Layer — Governance, Environments, Providers core

Four Pillars of the Engine

SYSTEM EXTENSIBILITY

Open at every layer Agents, Plugins, Clients — all extensible

Three SDKs. Three extension points. Complete control over the engine.

AGENT SDK

Custom Agents

Write agents in JavaScript with 63+ SDK modules — filesystem, git, browser, terminal, LLM, vector DB, memory, knowledge graphs. Full control over the agentic loop.

PLUGIN SDK

Custom Plugins

Three communication channels — WebSocket actions, multiplexed events, HTTP REST. Plugins run inside the engine. No separate agent instance needed.

CLIENT SDK

Custom Clients

72 REST API modules + 33 WebSocket modules. Build dashboards, mobile apps, Slack bots, VS Code extensions — anything that talks to the engine.

AGENT EXTENSIBILITY

Every agent is extensible Remix, Skills, Flows, Capabilities

Multiple ways to make agents more powerful — from no-code to full code.

Agent Types — From No-Code to Full Code

Remix Agents inherit from a base agent and add custom instructions in YAML+Markdown — no code required, git-friendly, composable. Flow Agents use a visual graph editor (LiteGraph) for drag-and-drop agent workflows. Custom Agents are pure code with full SDK access. Remote Agents run in external environments. All types share the same 675+ skill library.

            Remix Agent (no-code):
---
baseAgent: code-gen
supportedlanguages: [python]
---
Custom instructions here...

Flow Agent (visual):
[Node A] → [Node B] → [Node C]

Custom Agent (full code):
codebolt.onMessage(async (msg) => {
  // your logic, your tools
});

          

675+ Skills Across 72 Domains

Agents access skills organized across 72 tool domains — file operations, git, browser control, terminal, LLM, vector database, agent control, memory, knowledge graphs, and more. Skills are scoped by environment capabilities — the engine prevents agents from calling unavailable tools. Add skills, declare capabilities, set per-agent model preferences.

            72 tool domains:
├─ file (read, write, search, diff)
├─ git (commit, push, branch, merge)
├─ browser (navigate, click, screenshot)
├─ terminal (execute, stream, PTY)
├─ llm (chat, embed, count tokens)
├─ vectordb (store, query, search)
├─ agent (start, stop, list, spawn)
├─ memory (persist, retrieve, graph)
└─ ... 64 more domains
= 675+ individual tools

          
MULTI-AGENT SCALING

Multiple agents, one environment Coordination, not collision

Sub-agents, parallel execution, stigmergy, deliberation, and review — all within a single Codebolt instance.

Sub-Agent Spawning & Parallel Execution

An agent can spawn background child threads that run in parallel. Parent agents wait for individual completions, grouped completions, or any external event. Children are full agent instances with complete SDK access — not async tasks. Group multiple children and await batch completion. Message-driven communication between parent and children.

            Parent Agent
  ├─ spawn → Child 1 (review)
  ├─ spawn → Child 2 (test)
  ├─ spawn → Child 3 (docs)
  │
  └─ waitForGroup('batch-1')
          ↓
  All children complete
  → Merge results
  → Continue

          

Stigmergy, Deliberation & Auto Review

Agents coordinate through shared state (stigmergy), not fragile message passing. Pheromone-based task ownership prevents conflicts. Deliberation councils let agents propose, debate, vote, and reach consensus. The review-merge system lets agents review each other's work and auto-merge without GitHub PR bottleneck. Drift tracking catches deviation across all agents.

            Agent A: implements feature
Agent B: reviews (auto-assigned)
Agent C: checks for drift
      ↓
Deliberation if conflict
      ↓
Auto-merged. Traced. Auditable.
No human bottleneck.

          
MULTI-ENVIRONMENT SCALING

Chain environments together Proxy execution across machines

One environment's agent can trigger work in another. Chain them. Scale them. Any topology.

Proxy Execution — Environment Chaining

The RemoteExecutionPlugin bridges environments via WebSocket. Environment A's agent sends work to Environment B, which can forward to Environment C. Any topology — linear chains, trees, peer-to-peer. Each environment runs its own Codebolt instance with full capabilities. The proxy is plugin-based — not hardcoded — so any environment can claim the execution gateway.

            Env A (laptop)
  │ proxy execution
  ↓
Env B (Docker GPU)
  │ proxy execution
  ↓
Env C (cloud cluster)

Or: Env A ↔ Env B ↔ Env C (peer)
Or: Env A → [Env B, Env C, Env D] (fan-out)
Any topology. Plugin-based routing.

          

State Transfer & Lifecycle

Git bundles transfer workspace state between environments. The Narrative Engine snapshots per-environment with per-thread git refs. Full lifecycle management — CREATED, STARTING, RUNNING, STOPPING, STOPPED — with heartbeat monitoring every 30 seconds. The provider system treats local, Docker, cloud, and hierarchical environments identically.

            Environment Lifecycle:
CREATED → STARTING → RUNNING
                     ↕ heartbeat (30s)
STOPPING ← STOPPED ← ERROR

State Transfer:
Env A [snapshot] → git bundle
                → Env B [restore]
Bidirectional. Any topology.

          

Engine Internals

A Rust-based flight recorder capturing the full reasoning chain for every agent action. Shadow git for snapshot versioning. Per-thread commit history. Agent attribution for every change. Git bundle export for cross-environment transfer. Deterministic replay of any decision point. 12 snapshot operations including create, browse, merge, checkout, import/export.

Local Rust engine instances assess drift within each agent context — structural, scope, constraint, and coverage drift. The global JavaScript coordination layer aggregates signals across all agents, detecting systemic drift that no single agent would catch. When agents deviate from intent, the system flags it before it compounds.

The policy engine evaluates agent actions against configurable rules. Scoped by agent role, agent ID, environment, provider, and execution phase. LLM-based risk classification. Decisions: allow, deny, or escalate to human. Every decision logged for audit.

Episodic memory for time-based recall. Persistent memory with chunking, embedding, and retrieval pipelines. The Context Assembly Engine assembles optimal context from all memory types using rules, pipelines, and token budgets. Agents know what to remember and when.

The engine never calls platform APIs directly. It defines a HostBridge interface for process spawning, SQLite, Kuzu graph DB, and ONNX inference. Each runtime implements its own bridge: Electron uses UtilityProcess, CLI uses child_process and better-sqlite3, TUI connects via WebSocket proxy. One codebase, every runtime.

The engine that scales with your ambition.