beadloom 1.5.0

Context Oracle + Doc Sync Engine for AI-assisted development

Beadloom

Read this in other languages: Русский

Architecture as Code. Context as a Service.

Beadloom turns Architecture as Code into Architectural Intelligence — structured, queryable knowledge about your system that humans and agents consume in <20ms.

---

IDE finds code. Beadloom tells you what that code means in the context of your system — and enforces the boundaries.

Platforms: macOS, Linux, Windows  |  Python: 3.10+

Why Beadloom?

Large codebases lack Architectural Intelligence — structured, queryable knowledge about how the system is built and how its parts connect. Without it, your team makes decisions outside architectural boundaries — accumulating tech debt. Your agents hallucinate.

• "Only two people understand how this works." Architecture lives in heads, not in the repo. When they leave, the knowledge leaves with them.
• "The docs are lying." Documentation goes stale. Nobody notices until a developer or agent starts building new functionality on top of outdated specs.
• "Agents burn context on orientation, not work." Every session starts from scratch — grep, read, guess. The right 2K tokens matter more than a noisy 128K window.

Beadloom turns Architecture as Code into three queryable primitives:

1. Context Oracle — architecture graph in YAML, stored in Git. Query any node → deterministic context bundle in <20ms. Same query, same result, every time.

2. Doc Sync Engine — tracks code↔doc relationships. Catches stale documentation on every commit. No more "the spec says X but the code does Y".

3. Architecture Rules — boundary constraints in YAML, validated with beadloom lint, enforced in CI. Boundaries are checked at build time — not hoped for at review time.

For AI agents, beadloom prime assembles all three into a <2K-token payload — one command replaces the grep→read→guess loop.

Deterministic context, not probabilistic guessing

IDE indexers use semantic search — an LLM decides what's relevant. Beadloom uses deterministic graph traversal: BFS over an explicit architecture graph produces the same context bundle every time. The graph is YAML in Git — reviewable, auditable, version-controlled.

	Semantic search (IDE)	Beadloom
Answers	"Where is this class?"	"What is this feature and how does it fit?"
Method	Embeddings + LLM ranking	Explicit graph + BFS
Result	Probabilistic	Deterministic
Docs	Doesn't track freshness	Catches stale docs every commit
Architecture	Doesn't validate	Enforces boundaries, blocks violations
Knowledge	Dies with the session	Lives in Git, survives team changes

---

Research and industry trends

• Lost in the Middle (Liu et al., 2023) — LLMs lose accuracy on information buried in long contexts. The right 2K tokens beat a noisy 128K window.
• Context Engineering for Coding Agents (Fowler, 2025) — structured context is a core capability for coding agents, not a nice-to-have.
• From Scattered to Structured (Keim & Kaplan, KIT, 2026) — architectural knowledge dispersed across artifacts causes "architectural erosion"; consolidating it into a structured knowledge base is the fix.
• Why AI Coding Agents Aren't Production-Ready (Raja & Gemawat, VentureBeat, 2025) — practitioners at LinkedIn and Microsoft document how agents hallucinate without architectural context.
• Context Quality vs Quantity (Augment Code, 2025) — relationship-aware context reduces hallucinations by ~40% compared to naive context stuffing.
• State of Software Architecture 2025 (IcePanel, 2026) — keeping architecture docs current is the #1 challenge; teams lose trust in outdated documentation.
• 2026 Agentic Coding Trends (Anthropic, 2026) — the industry shifts to agent-orchestration with structured context.
• Architecture Reset (ITBrief, 2026) — enterprises pivot from "vibe coding" to architecture-first development.

---

Who is it for?

Tech Lead / Architect — You want architecture knowledge to be explicit, versionable, and survive team rotation. Beadloom makes the implicit explicit: domains, features, services, dependencies — all in YAML, all in Git. beadloom lint enforces boundaries in CI.

Platform / DevEx Engineer — You build tooling for the team. Beadloom gives your CI pipeline a doc freshness check and architecture boundary validation that actually work. Agents get structured context out of the box via MCP.

Individual Developer — You're tired of spending the first hour on every task figuring out "how does this part of the system work?" beadloom ctx FEATURE-ID gives you the answer in seconds.

AI-Assisted / Agent-Native Developer — You work with AI agents and need them to work within your architecture, not break it. beadloom prime + MCP gives your agent a compact, deterministic context payload at session start.

Key features

• Context Oracle — deterministic graph traversal, compact JSON bundle in <20ms
• Doc Sync Engine — tracks code↔doc relationships, detects stale documentation, integrates with git hooks
• Architecture as Code — define boundary rules in YAML, validate with beadloom lint, enforce in CI
• Agent Prime — single entry point for AI agents: beadloom prime outputs <2K tokens of architecture context, setup-rules creates IDE adapters, AGENTS.md carries conventions and MCP tools
• Full-text search — FTS5-powered search across nodes, docs, and code symbols
• Impact analysis — beadloom why shows what depends on a node and what breaks if it changes
• Code-first onboarding — bootstrap an architecture graph from code structure alone; no docs needed to start
• MCP server — 10 tools for AI agents, including write operations and search
• Interactive TUI — beadloom ui terminal dashboard for browsing the graph
• Local-first — single CLI + single SQLite file, no Docker, no cloud dependencies

How it works

Beadloom maintains an architecture graph defined in YAML files under .beadloom/_graph/. The graph consists of nodes (features, services, domains, entities, ADRs) connected by edges (part_of, uses, depends_on, etc.).

The indexing pipeline merges three sources into a single SQLite database:

1. Graph YAML — nodes and edges that describe the project architecture
2. Documentation — Markdown files linked to graph nodes, split into searchable chunks
3. Code — source files parsed with tree-sitter to extract symbols and # beadloom:domain=context-oracle annotations

When you request context for a node, the Context Oracle runs a breadth-first traversal, collects the relevant subgraph, documentation, and code symbols, and returns a compact bundle.

The Doc Sync Engine tracks which documentation files correspond to which code files. On every commit (via a git hook), it detects stale docs and either warns or blocks the commit.

Architecture as Code

Beadloom doesn't just describe architecture — it enforces it. Define boundary rules in YAML, validate with beadloom lint, and block violations in CI.

Rules (.beadloom/_graph/rules.yml) — real rules from this project:

rules:
  - name: domain-needs-parent
    description: "Every domain must be part_of the beadloom service"
    require:
      for: { kind: domain }
      has_edge_to: { ref_id: beadloom }
      edge_kind: part_of

  - name: feature-needs-domain
    description: "Every feature must be part_of a domain"
    require:
      for: { kind: feature }
      has_edge_to: { kind: domain }
      edge_kind: part_of

  - name: service-needs-parent
    description: "Every service must be part_of the beadloom service"
    require:
      for: { kind: service }
      has_edge_to: { ref_id: beadloom }
      edge_kind: part_of

  - name: no-domain-depends-on-service
    description: "Domains must not have depends_on edges to services"
    deny:
      from: { kind: domain }
      to: { kind: service }
      unless_edge: [part_of]

Validate:

beadloom lint                 # rich output in terminal
beadloom lint --strict        # exit 1 on violations (for CI)
beadloom lint --format json   # machine-readable output

Agent-aware constraints — when an agent calls get_context("why"), the response includes active rules for that node. Agents respect architectural boundaries by design, not by accident.

Supported languages for import analysis: Python, TypeScript/JavaScript, Go, Rust, Kotlin, Java, Swift, C/C++, Objective-C.

Install

uv tool install beadloom        # recommended
pipx install beadloom            # alternative

Quick start

# 1. Scan your codebase and generate an architecture graph
beadloom init --bootstrap

# 2. Review the generated graph (edit domains, rename nodes, add edges)
vi .beadloom/_graph/services.yml

# 3. Build the index and start using it
beadloom reindex
beadloom ctx search              # get context for a feature
beadloom sync-check                # check if docs are up to date
beadloom lint                      # check architecture rules

# 4. Set up context injection for AI agents
beadloom setup-rules               # create IDE adapter files
beadloom prime                      # verify: see what your agent will see

No documentation required to start — Beadloom bootstraps from code structure alone.

Agent Prime — one command, full context

Beadloom injects context into AI agents through a three-layer architecture:

1. IDE adapters — beadloom setup-rules creates .cursorrules, .windsurfrules, .clinerules that point to .beadloom/AGENTS.md
2. AGENTS.md — project conventions, architecture rules from rules.yml, MCP tool catalog — loaded automatically by the agent
3. beadloom prime — dynamic context payload (<2K tokens): architecture summary, health metrics, active rules, domain map

For programmatic access, connect via MCP:

{
  "mcpServers": {
    "beadloom": {
      "command": "beadloom",
      "args": ["mcp-serve"]
    }
  }
}

Works with Claude Code, Cursor, Windsurf, Cline, and any MCP-compatible tool.

CLI commands

Command	Description
init --bootstrap	Scan code and generate an initial architecture graph
init --import DIR	Import and classify existing documentation
reindex	Rebuild the SQLite index from graph, docs, and code
ctx REF_ID	Get a context bundle (Markdown or --json)
graph [REF_ID]	Visualize the architecture graph (Mermaid or JSON)
search QUERY	Full-text search across nodes, docs, and code symbols
status	Project index statistics and documentation coverage
doctor	Validate the architecture graph
sync-check	Check doc↔code synchronization status
sync-update REF_ID	Review and update stale docs
docs generate	Generate documentation skeletons from the architecture graph
docs polish	Generate structured data for AI-driven documentation enrichment
lint	Validate code against architecture boundary rules
why REF_ID	Impact analysis — upstream deps and downstream dependents
diff	Show graph changes since a git ref
link REF_ID [URL]	Manage external tracker links on graph nodes
ui	Interactive terminal dashboard (requires beadloom[tui])
watch	Auto-reindex on file changes (requires beadloom[watch])
install-hooks	Install the beadloom pre-commit hook
prime	Output compact project context for AI agent injection
setup-rules	Create IDE adapter files (.cursorrules, .windsurfrules, .clinerules)
setup-mcp	Configure MCP server for AI agents
mcp-serve	Run the MCP server (stdio transport)

MCP tools

Tool	Description
prime	Compact project context for AI agent session start
get_context	Context bundle for a ref_id (graph + docs + code symbols + constraints)
get_graph	Subgraph around a node (nodes and edges as JSON)
list_nodes	List graph nodes, optionally filtered by kind
sync_check	Check if documentation is up-to-date with code
get_status	Documentation coverage and index statistics
update_node	Update a node's summary or metadata in YAML and SQLite
mark_synced	Mark documentation as synchronized with code
search	Full-text search across nodes, docs, and code symbols
generate_docs	Generate structured documentation data for AI-driven enrichment

Configuration

All project data lives under .beadloom/ in your repository root:

• .beadloom/config.yml — scan paths, languages, sync engine settings
• .beadloom/_graph/*.yml — architecture graph definition (YAML, version-controlled)
• .beadloom/_graph/rules.yml — architecture boundary rules
• .beadloom/AGENTS.md — project conventions and MCP tool catalog for AI agents
• .beadloom/beadloom.db — SQLite index (auto-generated, add to .gitignore)

Link code to graph nodes with annotations:

# beadloom:domain=doc-sync
def check_freshness(db: sqlite3.Connection, ref_id: str) -> SyncStatus:
    ...

Documentation structure

Beadloom uses a domain-first layout. Here is the actual structure from this project:

docs/
  architecture.md                                  # system design
  getting-started.md                               # quick start guide
  guides/
    ci-setup.md                                    # CI integration
  domains/
    context-oracle/
      README.md                                    # domain overview
      features/
        cache/SPEC.md                              # L1+L2 cache spec
        search/SPEC.md                             # FTS5 search spec
        why/SPEC.md                                # impact analysis spec
    graph/
      README.md
      features/
        graph-diff/SPEC.md
        rule-engine/SPEC.md
        import-resolver/SPEC.md
    doc-sync/
      README.md
    onboarding/
      README.md
    infrastructure/
      README.md
      features/
        doctor/SPEC.md
        reindex/SPEC.md
        watcher/SPEC.md
  services/
    cli.md                                         # 21 CLI commands
    mcp.md                                         # 10 MCP tools
    tui.md                                         # TUI dashboard

Each domain gets a README.md (overview, invariants, API). Each feature gets a SPEC.md (purpose, data structures, algorithm, constraints).

Context bundle example

beadloom ctx why --json returns a deterministic context bundle — graph, docs, and code symbols assembled via BFS in <20ms:

{
  "version": 2,
  "focus": {
    "ref_id": "why",
    "kind": "feature",
    "summary": "Impact analysis — upstream deps and downstream consumers via bidirectional BFS"
  },
  "graph": {
    "nodes": [
      { "ref_id": "why", "kind": "feature", "summary": "Impact analysis ..." },
      { "ref_id": "context-oracle", "kind": "domain", "summary": "BFS graph traversal, caching, search" },
      { "ref_id": "beadloom", "kind": "service", "summary": "CLI + MCP server" },
      { "ref_id": "search", "kind": "feature", "summary": "FTS5 full-text search" },
      { "ref_id": "cache", "kind": "feature", "summary": "ETag-based bundle cache" }
    ],
    "edges": [
      { "src": "why", "dst": "context-oracle", "kind": "part_of" },
      { "src": "context-oracle", "dst": "beadloom", "kind": "part_of" },
      { "src": "cli", "dst": "context-oracle", "kind": "uses" }
    ]
  },
  "text_chunks": ["... 10 doc chunks from SPEC.md files ..."],
  "code_symbols": ["... 146 symbols from traversed modules ..."],
  "sync_status": { "stale_docs": [], "last_reindex": "2026-02-13T..." }
}

BFS depth=2 from why traverses: why → context-oracle (parent domain) → sibling features (search, cache), services (cli, mcp-server), cross-domain deps (infrastructure, graph) — 10 nodes, 12 edges total.

Beads integration

A context loom for your beads.

Beadloom complements Beads by providing structured context to planner/coder/reviewer agents. Beads workers call get_context(feature_id) via MCP and receive a ready-made bundle instead of searching the codebase from scratch.

Beadloom works independently of Beads — the integration is optional.

Development

uv sync --dev              # install with dev dependencies
uv run pytest              # run tests
uv run ruff check src/     # lint
uv run ruff format src/    # format
uv run mypy                # type checking (strict mode)

Docs

Document	Description
architecture.md	System design and component overview
getting-started.md	Quick start guide
Domains
Context Oracle	BFS algorithm, context assembly, caching, search
Cache	L1 in-memory + L2 SQLite bundle cache
Search	FTS5 full-text search
Why	Impact analysis via bidirectional BFS
Graph	YAML graph format, diff, rule engine, linter
Graph Diff	Git ref comparison for graph changes
Rule Engine	Architecture-as-Code deny/require rules
Import Resolver	Multi-language import analysis
Doc Sync	Doc↔code synchronization engine
Onboarding	Project bootstrap and presets
Infrastructure	Database, health metrics, reindex
Doctor	Graph validation checks
Reindex	Full and incremental reindex pipeline
Watcher	Auto-reindex on file changes
Services
CLI Reference	All 21 CLI commands
MCP Server	All 10 MCP tools for AI agents
TUI Dashboard	Interactive terminal dashboard
Guides
CI Setup	GitHub Actions / GitLab CI integration

Known Issues

See UX Issues Log for the full list of known issues.

License

MIT