Authentication & API Keys — ContextNest Community distinguishes two kinds of key, and it is worth keeping them straight:
CLI Reference — The Context Nest CLI (ctx) is a structured, versioned knowledge base your AI agents can query. It provides commands for setting up vaults, creating and…
Compatibility: Git, Obsidian & AI Agents — Context Nest is designed to work with existing tools and workflows. Context Nest vaults are git-friendly by design. All files are plain text (Markdown…
Context Nest Specification — The Context Nest Specification is the canonical reference for the protocol. It defines the complete format, rules, and behavior that implementations must…
MCP Server — The ContextNest (Community) server exposes vault operations as MCP tools that any MCP-compatible AI client can call. Every tool is named context (with a…
REST API Reference — A concise reference to the ContextNest Community (hosted-nest) REST API. It is faithful to the server's API.md; only endpoints that actually exist are…
Self-Hosting (Community Edition) — ContextNest Community Edition is a self-hosted context governance server for AI workflows, part of the PromptOwl platform. It stores, versions, and…
Validation Rules — Context Nest defines validation rules for documents, source nodes, and cross-references. Run validation with:
Vault & Registry Configuration — Context Nest reads configuration from two places: The central registry holds a vaults: map (alias → local vault), an optional remotes: map (alias → hosted…
Addressing Overview — Context Nest uses the contextnest:// URI scheme to address documents, sections, tags, and folders within a vault.
Cross-Vault Federation — Federation enables cross-namespace URI resolution — referencing documents in other vaults.
URI Format — The contextnest:// URI scheme follows RFC 3986 conventions. Implementations must normalize URIs before resolution:
URI Resolution — Resolution is the process of converting a contextnest:// URI into a document or set of documents.
Core Concepts — Context Nest is built on a small set of composable concepts. Understanding these gives you the full picture of how vaults work.
Context Index — The context.yaml file is the machine-readable manifest of a Context Nest vault. It is auto-generated by the CLI and serves as the primary entry point for…
Frontmatter — Every Context Nest document begins with a YAML frontmatter block delimited by ---. The frontmatter contains structured metadata that the resolver…
Node Types — Every document in a Context Nest vault has a type field in its frontmatter. The type tells agents how to interpret the content.
Status Lifecycle — Every document in a nest carries a status that governs where it is in its life and whether retrieval can see it. ContextNest uses a five-state lifecycle —…
Vault Structure — A Context Nest vault is a directory containing Markdown documents, configuration, and version history.
Context Packs Overview — Context packs are curated bundles of documents with agent instructions. They let you define named collections of context that agents can request by name.
Cloud Packs — Cloud packs will be hosted on the PromptOwl platform and queryable without downloading source files.
Pack Format — Context packs are YAML files stored in the packs/ directory. Static packs use includes to list specific documents:
Distillation — Distillation is the one-pass operation at the heart of ContextNest: point the engine at a folder — a codebase, a docs tree, or an existing vault — and it…
Querying & Tracing — Agents request context by address (URI) or by selector query. The resolver returns only published content, with full tracing of what was accessed.
Query Tracing — Every context query produces trace entries that record what was accessed, when, and by what version. Traces provide a provenance chain from knowledge…
Quick Start — Get a Context Nest vault running in under 2 minutes. By the end, you'll have a versioned, queryable knowledge vault that any AI agent can read.
Add Documents — This creates nodes/api-design.md from a frontmatter template as version 1, and regenerates the index. Tags accept a comma- or space-separated list; you…
Create a Vault — Starter recipes scaffold a vault with documents, packs, and agent instructions tailored to a role:
Install the ctx CLI — The package installs with a flattened dependency tree — its runtime dependencies are bundled/flattened so a global install pulls a self-contained CLI…
Query Context — Context Nest gives you two ways to pull from your vault: ctx resolve for a metadata list of matches, and ctx query for full, graph-aware context retrieval.
Remote & Governed Nests — A nest does not have to live on your local disk. ContextNest can register remote nests and route reads and writes to them over MCP — the same ctx commands…
Selectors Overview — Selectors are the composable query grammar for Context Nest. They let you precisely describe which documents you want — by tag, type, status, pack, node…
Selector Atoms — Atoms are the building blocks of selector expressions. Each atom matches documents based on a single criterion.
Selector Examples — Real-world selector patterns for common use cases.
Selector Operators — Operators combine atoms into compound expressions. Parentheses control evaluation order. Use them whenever you mix operators, rather than relying on…
Vault-Hosted Skills — ContextNest lets a vault host reusable skills — governed procedures an agent runs when a matching situation comes up. A skill is not a separate kind of…
Source Nodes Overview — Source nodes are documents whose body contains instructions for fetching live data from external services. They are first-class nodes in the context graph…
Dependencies & Ordering — Source nodes can depend on other source nodes. The resolver uses these dependencies to determine hydration order — ensuring upstream data is available…
Source Frontmatter — Source nodes include a source block in their frontmatter with structured metadata for the resolver and runtime.
Writing Source Nodes — The markdown body of a source node is an instruction set for agents. Write it as a clear, step-by-step runbook.
Vault Registry & Multi-Vault — ContextNest keeps a central vault registry so you can work with many nests from any directory. The registry maps a short alias to a nest — a local path or…
Versioning & Integrity — Context Nest provides a tamper-evident version history for every document, with cryptographic hash chains and vault-level checkpoints.
Integrity Verification — Context Nest uses SHA-256 hash chains to make version history tamper-evident. Each version's chain hash depends on all previous versions. Changing any…
Nest Checkpoints — A nest checkpoint is an atomic, immutable snapshot of the entire vault — the Context Nest equivalent of a git commit.
Storage Model — Version history uses a keyframe + change-log model for storage efficiency. Keyframes are full snapshots stored as separate vN.md files; every intermediate…