<!--
Sitemap:
- [Installation](/installation): Install the Bento daemon on macOS or Linux, then write your first pipeline to run a coding agent on a GitHub, Linear, or schedule event.
- [Upgrading](/upgrading): Version-specific steps for upgrading an existing Bento install.
- [Concepts](/concepts)
- [Build your first pipeline](/tutorials/pipeline-args)
- [Target a specific issue or PR from a URL](/tutorials/url-targeting)
- [Keep state across runs](/tutorials/pipeline-state)
- [Fire a pipeline on a schedule or on demand](/tutorials/schedule-and-fire)
- [Deploy a box to Railway](/tutorials/deploy-to-railway)
- [Operate a hosted daemon](/tutorials/operate-a-hosted-daemon)
- [Configuration](/configuration): Configure the Bento daemon with daemon.yaml: service name, port, webhooks, sandboxes, knowledge base, and environment variables.
- [Members](/members)
- [Knowledge base](/knowledge-base/)
- [Method and delivery](/knowledge-base/modes): Choose how Bento retrieves knowledge (BM25, vector, or hybrid) and how it delivers that knowledge to a coding agent.
- [Config](/knowledge-base/config)
- [MCP](/knowledge-base/mcp): Give coding agents your team knowledge over MCP. The Bento daemon serves an ask_knowledge search tool and per-file resources.
- [Pipeline configuration reference](/pipelines/config): Reference for Bento pipeline YAML: triggers, agents, skills, instructions, filters, sandboxes, structured results, and outputs.
- [Filters](/pipelines/filters): Filter GitHub, Linear, and webhook events by repository, label, and other fields so only the right Bento pipelines run.
- [Triggers](/triggers/): Start a Bento pipeline from a GitHub, Linear, webhook, schedule, or manual trigger. Compare the trigger types and when each one fires.
- [GitHub trigger](/triggers/github): Run a coding agent on GitHub pull request, issue, and other webhook events. Configure HMAC verification and event patterns.
- [Linear trigger](/triggers/linear): Run a coding agent on Linear issue and comment events. Configure the Linear webhook, signature verification, and Hookdeck relay.
- [Webhook trigger](/triggers/webhook): Fire a Bento pipeline from any HTTP POST to /webhooks/{name}, with bearer-token authentication declared in daemon.yaml.
- [Schedule trigger](/triggers/schedule)
- [Manual trigger](/triggers/manual): Fire any Bento pipeline on demand with bento trigger fire, and pass typed inputs to a pipeline that runs only on request.
- [Traces](/pipelines/traces)
- [Slack](/integrations/slack)
- [Public access](/public-access): Expose the Bento daemon to GitHub webhooks through a Cloudflare Quick Tunnel or Tailscale Funnel, and compare the two options.
- [Context engineering](/context-engineering): Assemble each coding agent prompt from personas, policies, skills, and pipeline instructions. Learn which file each instruction belongs in.
- [Best practices](/best-practices)
- [Troubleshooting](/troubleshooting)
- [Architecture](/architecture/vision)
- [Workspaces](/workspaces)
- [Authentication](/authentication)
- [Identity](/identity)
- [Security](/security)
- [References](/references)
- [Changelog](/changelog): Bento release history.
- [CLI reference](/cli/)
- [Setup](/cli/setup)
- [Secrets](/cli/secrets)
- [Lifecycle](/cli/lifecycle)
- [Sandbox image](/cli/image)
- [Sandboxes](/cli/sandbox)
- [Observability](/cli/observability)
- [Diagnostics](/cli/diagnostics)
- [Triggers](/cli/triggers)
- [Workbench](/cli/workbench)
- [Auth](/cli/auth)
- [Knowledge](/cli/knowledge)
- [Evals](/cli/evals)
- [Bento docs: run coding agents from version-controlled pipelines](/index): Bento runs coding agents from pipelines you keep in your repository. Declare the trigger, sandbox, skill, and guardrails in YAML.
- [Runtime wrapper](/architecture/runtime-wrapper)
- [Skill evolve](/architecture/skill-evolve)
-->

# Architecture

Bento is structured in three layers.

## Layer 1: Agent infrastructure

A daemon that manages persistent AI agents. Process supervision, scheduling, Telegram/Slack interface. The runtime.

## Layer 2: Context synthesis

Every session, meeting, ticket, and conversation gets tagged and indexed. Cross-channel recall — "what do we know about auth?" pulls from Slack, Linear, GitHub, Telegram, and shared sessions. The memory.

## Layer 3: Company brain

Ingest from all sources — Granola meetings, email, support tickets, code reviews. Organize by project, topic, team. Surface as executable skills and queryable knowledge via MCP. The intelligence layer.

```
Sources                    Bento                        Consumers
─────────                  ───────                     ─────────
Shared sessions    ──┐                           ┌──  Claude Code
Granola meetings   ──┤     ┌───────────────┐     ├──  Codex
CRM (Attio)        ──┼────>│  Tag + Index  │────>├──  pi
Email              ──┤     └───────────────┘     ├──  Slack bot
Linear issues      ──┤        by project /       ├──  Telegram
GitHub activity    ──┘        topic / team        └──  Dashboard
```

## The MCP interface

Bento exposes the brain as an MCP server. Any MCP-compatible agent connects to it and reaches the accumulated knowledge and skills of the company.

## Access control

Raw knowledge ingestion is one thing. What the server returns depends on who asks.

### Redaction

Strip sensitive data before it enters the knowledge base, or strip it at query time. This covers personally identifiable information, API keys, credentials, and customer data.

### Scoping

Not everyone sees everything. The agent of an external contractor never receives context from an internal strategy discussion. Scope by team, by project, or by role.

### Projection

Shape output for the consumer. An agent doing code review gets technical decisions and architecture context.

```yaml
access:
  layers:
    - name: internal
      tags: [strategy, hr, finance]
      visibility: team-only

    - name: redacted
      rules:
        - strip: [api_keys, credentials, pii]
        - mask: [customer_names, revenue_figures]

    - name: public
      tags: [engineering, architecture, conventions]
      visibility: anyone

projections:
  code-review:
    include_tags: [architecture, conventions, tech-decisions]
    exclude_tags: [finance, hr]

  onboarding:
    include_tags: [architecture, conventions, team-structure, processes]
```

The MCP server is the policy enforcement point. Raw data stays on bento. Consumers get a filtered view.

## Architecture reading order

To learn about Bento architecture, read these pages in order:

1. **[Context engineering](/context-engineering)** — how bento assembles an agent prompt from the persona, the skill, and the context
2. **[Runtime wrapper](/architecture/runtime-wrapper)** — normalized metric collection across the `pi`, `claude`, and `codex` runtimes
3. **[Skill evolve](/architecture/skill-evolve)** — automated skill improvement from session history

## References

* [Karpathy on company-level AI](https://x.com/karpathy/status/2039805659525644595)
