DocNexus — Local Project Memory for Agents

    1

    Local, source-attributed project memory for coding agents: capture reviewed Markdown, search and recall it offline, and keep architecture decisions grounded in evidence.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    DocNexus — Local Project Memory for Agents

    Example session with this skill installed

    Use DocNexus to answer from our project memory:

    Why do refresh tokens rotate on every use, where is that decision recorded, and what evidence supports it? Cite the stored source and call out any conflicts.

    • Read your context and instructions
    • Compiled the docnexus

    Answer

    DocNexus found one current decision record and one supporting source. The policy is to rotate a refresh token on every successful use, issue a replacement pair, and revoke the complete token family if an already-used token is replayed.

    Evidence

    ClaimEvidenceLocation
    Refresh tokens rotate after every successful refreshThreat-model decision and implementation notedocnexus/library/auth/token-rotation.md
    Reuse revokes the full token familySecurity review accepted 2026-10-14docnexus/records/auth-001/metadata.json
    Revocation is atomic with token issuanceTransaction boundary noted in implementationsrc/auth/token-service.ts
    Two older records conflict about rotation timingLegacy note says daily rotation; replacement record supersedes itdocnexus/records/auth-000/timeline.md

    Current decision

    The active policy rotates the refresh token on every use. The new token is written in the same transaction that invalidates the previous token. Detection of reuse revokes the whole family rather than returning a generic authentication error.

    Provenance

    • Source: docnexus/records/auth-001/source.md
    • Timeline: docnexus/records/auth-001/timeline.md
    • Current document: docnexus/library/auth/token-rotation.md
    • Superseding record: auth-001
    • Older conflicting record: auth-000

    Next steps

    1. Treat auth-001 as the authoritative decision.
    2. Run docnexus document get --id auth-001 --include document,source,timeline before changing token behavior.
    3. Update the affected knowledge page if the transaction boundary changes.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    DocNexus — Local Project Memory for Agents

    DocNexus keeps curated project knowledge in Markdown next to a source-attributed timeline. Six coordinated skills let Codex, Claude Code, and other SKILL.md agents capture decisions, retrieve prior context, cite evidence, maintain indexes, and recover from Git changes without sending project knowledge to an external LLM.

    What it does

    • Durable project memory — current Markdown documents plus records containing the original source, metadata, timeline, and provenance.
    • Hybrid recall — keyword retrieval reads text directly; semantic recall fuses keyword and local vector ranks with one-hop graph evidence.
    • Offline by default — the bundled quantized ONNX model runs locally; the CLI makes no external LLM calls.
    • Review before write — capture flows extract and seal drafts, show a preview, and only ingest after the user authorizes the change.
    • Maintenance — validates canonical text, rebuilds PGLite or Postgres/pgvector projections, and repairs derived concept and graph indexes.
    • Agent-native — the six skills route capture, extraction, ingestion, recall, library operations, and maintenance automatically.

    How it works

    Install the npm package inside the target project, initialize an agent integration, then ask the agent to remember a decision or answer from memory. A write runs through draft → seal → preview → authorization → ingest. Reads return complete documents and library paths for citation instead of unverified snippets.

    Requirements and breaking change

    Requires Node.js 22.13+ and npm. Workspace format 7 is used by current releases. On versions 0.24.2+, npm postinstall deletes recognized legacy workspaces from formats 1–6 without confirmation, migration, or backup. Back up any existing workspace before installing. Source checkouts and unrecognized directories are not affected.

    Current workspace format 7 requires fresh initialization. Installing 0.24.2+ deletes recognized legacy workspaces (formats 1–6) without migration or backup, so back up first. Refined documents are capped at 4,000 Unicode characters. Semantic recall requires a local index; keyword reads still work without it. Git hooks skip non-Git projects, and rebases or renames may need manual document-level recovery.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    • Free with an Agensi account

    Requires

    Node.js
    Git
    npm
    caches
    vitest
    installs
    Linux only
    cache

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables

    File Scopes

    .docnexus/**
    docnexus/**
    .git/**
    AGENTS.md
    CLAUDE.md

    Read/write access covers the .docnexus workspace, the configured Markdown knowledge directory, Git hooks, and agent instruction files. Network and environment variables are used only for npm dependencies or optional external PostgreSQL; the CLI makes no external LLM calls.

    Listed5 days ago

    What's inside

    Frequently Asked Questions

    DocNexus keeps current knowledge as project-local Markdown and preserves the source, metadata and timeline for every record. Agents search or recall that evidence before answering, which makes stale or conflicting project context visible instead of relying on memory or an unstructured wiki.

    Requires Node.js 22.13+ and npm. The six skills work with Codex, Claude Code and other SKILL.md agents. PGLite is the zero-configuration default; an existing PostgreSQL + pgvector database is optional.

    Unlike basic prompting, DocNexus uses a hybrid retrieval system (keyword + vector + graph evidence) and a strict metadata schema to ensure the agent retrieves factual project history instead of hallucinating details.

    The ZIP includes six SKILL.md workflows, the DocNexus CLI source, schemas, bundled local embedding files, documentation and tests, plus the setup and Git-hook integration code. npm installs dependencies. Versions 0.24.2+ delete recognized legacy workspaces without migration or backup, so back up before upgrading.

    Each refined document is limited to 4,000 rendered Unicode characters. Capture splits longer material into self-contained topic drafts. Keyword search reads canonical text directly; semantic recall additionally needs a local vector index.

    New in LLM Ops