A package manager for AI agent capabilities — scripts, skills, commands, agents, knowledge, memories, workflows, wikis, vaults, lessons, and scheduled tasks — that works with any AI coding assistant that can run shell commands.
akm gives agents a curated, searchable library built from local directories, GitHub repos, npm packages, and websites. Instead of front-loading a giant prompt, agents pull exactly what they need, when they need it, and feed results back so the library improves over time.
Option 1 — Prebuilt binary (recommended, no runtime required):
# Linux / macOS
curl -fsSL https://github.com/itlackey/akm/releases/latest/download/install.sh | bash
# Windows (PowerShell)
irm https://github.com/itlackey/akm/releases/latest/download/install.ps1 | iexOption 2 — Bun (requires Bun >= 1.0):
bun install -g akm-cliUpgrade in place: akm upgrade
AKM 0.8 requires the Bun runtime or the prebuilt binary. Node.js is not supported in this release. Cross-runtime compatibility is planned for 0.9.0. See Privacy & data for details on what akm stores locally.
git clone https://github.com/itlackey/akm.git
cd akm
bun install
bun run build- Manage sources — add local dirs, git repos, npm packages, and websites as searchable asset sources (details)
akm add github:owner/stash # GitHub akm add https://docs.example.com # crawled website
- Search a unified index — one FTS5 index across all your sources (details)
akm search "deploy" --type script --limit 5 - Curate a shortlist — get the best-match assets for a task without knowing exact names (details)
akm curate "set up a kubernetes deployment" - Load assets on demand — show the full content of any asset by ref (details)
akm show workflow:ship-release
- Capture local knowledge — save discoveries as memories, imported docs, or wiki pages (details)
akm remember "Staging deploys require VPN" akm import ./notes/runbook.md --wiki ops - Run structured workflows — parse, start, step through, and resume multi-step procedures (details)
akm workflow start workflow:onboarding
- Improve continuously — feedback drives proposals; proposals drive asset quality (details)
akm feedback skill:code-review --positive akm improve && akm proposal list
akm setup # guided first-time setup
akm add github:itlackey/akm-stash # install the official onboarding stash
akm index # build the search index
akm curate "deploy" # get a curated shortlist
akm show workflow:deploy # load the best match
akm remember "Deployment needs VPN" # capture a memory
akm feedback workflow:deploy --positiveFor non-interactive setup: akm setup --yes (or --dir ~/custom-stash for a custom path).
See docs/getting-started.md for a full walkthrough.
| Type | What it is | Example ref |
|---|---|---|
| script | Executable shell or code automation | script:deploy.sh |
| skill | A set of agent instructions | skill:code-review |
| command | A prompt template with placeholders | command:summarize |
| agent | System prompt + model + tool policy | agent:reviewer |
| knowledge | A reference document | knowledge:api-guide |
| vault | Key/value environment config (keys only, never secrets) | vault:prod-env |
| workflow | Structured multi-step procedure with resumable run state | workflow:ship-release |
| wiki | A page inside a multi-wiki knowledge base | wiki:ops/runbook |
| lesson | Distilled feedback insight | lesson:prefer-dry-run |
| memory | Recalled context from a previous session | memory:vpn-note |
See docs/concepts.md for classification rules and the ref format.
Add and search a stash
akm add github:owner/team-stash
akm index
akm search "database migration" --type script
akm show script:migrate.shCapture and route knowledge
akm remember "Hot-fix deploys skip staging" --target team-stash
akm import ./incident-report.md --wiki ops
akm wiki create opsBuild a living wiki (Karpathy LLM wiki pattern)
akm wiki create research # scaffold wikis/research/ with schema/index/log/raw/
akm wiki stash research https://arxiv.org/abs/2404.01744 # fetch raw source into raw/
akm wiki stash research ./notes/meeting.md # stash local notes as immutable raw
akm wiki ingest research # dispatch defaults.agent to run the ingest workflow end-to-endakm implements Andrej Karpathy's LLM wiki pattern: raw sources live in raw/ (immutable), the agent writes synthesized pages alongside them, and a schema.md rulebook keeps the voice and structure consistent across sessions. akm surfaces paths and invariants; your agent does the writing. See docs/wikis.md.
Improvement loop
akm feedback skill:planner --negative --reason "Doesn't account for merge conflicts"
akm improve # generate proposals from feedback + history
akm proposal list # review pending proposals
akm proposal accept <uuid-or-ref> # apply a proposal
akm proposal reject <uuid-or-ref> # discard itClone and customize an asset
akm clone workflow:ship-release --dest ./project/.claude
# edit the local copy — it wins in subsequent searches automaticallyakm tracks which assets agents actually use (select events) and what agents think of them (akm feedback). Running akm improve processes that signal to generate proposals — suggested edits, promotions, or deprecations. Review with akm proposal list, then akm proposal accept or akm proposal reject. Accepted changes write back to your writable sources. Distilled lessons surface via akm improve --distill.
Add this to your AGENTS.md, CLAUDE.md, or system prompt:
## Resources & Capabilities
You have access to a searchable library of scripts, skills, commands, agents,
knowledge, workflows, vaults, wikis, lessons, and memories via the `akm` CLI.
Use `akm -h` for details.No plugins or SDKs required. Platform-specific integrations are available in akm-plugins.
| Repo | What it is |
|---|---|
| itlackey/akm-stash | Official stash — ready-made skills, workflows, commands, and knowledge |
| itlackey/akm-plugins | Optional editor and agent integrations (OpenCode, etc.) |
| itlackey/akm-registry | Official registry index — pre-configured in every akm install |
| itlackey/akm-bench | Benchmark harness for measuring agent performance with akm |
| itlackey/akm-eval | Eval framework and tools for akm asset quality |
| Feature | Description |
|---|---|
| Search & Discovery | Build the index, search, curate a shortlist, and load assets by ref |
| Knowledge Management | Capture memories, import docs, manage wikis, and store config in vaults |
| Sources & Registries | Connect local dirs, git repos, npm packages, and websites; browse the registry |
| Workflows | Structured multi-step procedures with resumable run state |
| The Improvement Loop | Feedback, history, proposals, and automated asset improvement |
| Agent Integration | Wire akm into Claude Code, OpenCode, Cursor, and other coding assistants |
| Doc | Description |
|---|---|
| Getting Started | Install, first-time setup, add sources, search, show |
| Concepts | Sources, registries, asset types, refs, and the stash |
| CLI Reference | All commands and flags |
| Configuration | Settings, providers, embedding, and Ollama setup |
| Stash Maker's Guide | Build, publish, and share your own stashes |
| Registry | Registries, the index format, and private registry setup |
| Wikis | Multi-wiki knowledge bases |
| Release Notes — 0.8.0 | Latest release notes and migration guide |
| Stability policy | Which CLI surfaces are stable, evolving, or experimental |
| Security policy | Threat model and how to report vulnerabilities |
| Changelog | Per-release behavior changes |
AKM stores data locally and has no remote telemetry. Events, proposals, and improve history are written to ~/.local/share/akm/state.db. Registry packages and config backups go to ~/.cache/akm/. Nothing leaves your machine except requests to sources you explicitly configure (GitHub, npm, your own LLM endpoint).
See docs/data-and-telemetry.md for the complete on-disk inventory, event type reference, and instructions for inspecting or clearing local data.