AI coding agents forget. They forget across sessions, and they forget across tools. A decision you reached in Claude Code at midnight is invisible to Cursor the next morning. Honeycomb fixes that. Learn something once; recall it everywhere,
# Add to your Claude Code skills
git clone https://github.com/legioncodeinc/honeycombhoneycomb is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by legioncodeinc. AI coding agents forget. They forget across sessions, and they forget across tools. A decision you reached in Claude Code at midnight is invisible to Cursor the next morning. Honeycomb fixes that. Learn something once; recall it everywhere,. It has 59 GitHub stars.
honeycomb's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/legioncodeinc/honeycomb" and add it to your Claude Code skills directory (see the Installation section above).
honeycomb is primarily written in TypeScript. It is open-source under legioncodeinc on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh honeycomb against similar tools.
No comments yet. Be the first to share your thoughts!
Unlocks once the catalog security scan passes (runs nightly).
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
AI coding agents forget. They forget across sessions, and they forget across tools. A decision you reached in Claude Code at midnight is invisible to Cursor the next morning. Honeycomb fixes that. A local daemon captures what happens on every turn, distills it, and serves it back to any harness that asks. Learn something once; recall it everywhere, on any machine, in any tool, for anyone on your team.
New here? One command and you're on a dashboard. Jump to Install. Β· Want the docs? Everything lives at theapiary.sh.
Stop re-explaining your project to a fresh agent every morning. Honeycomb remembers your decisions, your conventions, and the fixes that worked, then primes your next session with them automatically. One install command, a friendly dashboard, no SQL, no config gauntlet.
One shared brain across every developer, device, and coding tool. A skill discovered by one engineer propagates to the whole team on their next session. Tenancy is enforced at the storage layer; credentials live behind a single loopback boundary; everything is versioned and auditable.
A vector database can store text and hand it back by similarity. Honeycomb does that, and then keeps going. On top of Activeloop Deep Lake, Legion Code builds the memory system that turns raw recall into a brain your agents actually trust:
No Node? No npm? No problem. The installer detects and sets up everything, then opens a dashboard in your browser. The terminal is just a progress log; the product is the first thing you touch.
# macOS / Linux
curl -fsSL https://get.theapiary.sh | sh
# Windows (PowerShell)
irm https://get.theapiary.sh/install.ps1 | iex
That single line installs a current Node/npm if missing, installs @legioncodeinc/honeycomb globally, brings up the daemon on 127.0.0.1:3850, opens the dashboard, and sets up HiveDoctor, a tiny watchdog that keeps it all healthy (opt out with --no-hivedoctor). Then:
Already running Hivemind? The dashboard detects it, explains that running both is unsupported, and "Proceed with Honeycomb" migrates you cleanly. Prefer to inspect before you pipe? The script and a published
SHA256SUMSare served from get.theapiary.sh.
git clone https://github.com/legioncodeinc/honeycomb.git
cd honeycomb
npm install
npm run build # tsc + esbuild β bundle/cli.js, daemon, harness, MCP, embed bundles
node bundle/cli.js setup # detect your assistants, wire hooks, start the daemon
node bundle/cli.js status # check the daemon and your environment
setup wires every coding assistant it detects and starts the loopback daemon; any storage command auto-starts the daemon if it is down. You'll need Activeloop Deep Lake credentials; the device flow above writes them to the shared ~/.deeplake/credentials.json.
# Capture a decision onceβ¦
honeycomb remember "we deploy from the prd-022 branch, never from main"
# β¦recall it anywhere: same daemon, same Deep Lake, any harness
honeycomb recall "how do we deploy"
Write it from Claude Code; recall it from Cursor tomorrow on a different laptop. That's the whole point.
Honeycomb is a long-lived local daemon plus thin clients. The daemon is the only process that talks to storage. Every harness, the CLI, the MCP server, and the SDK reach it over loopback HTTP. One shared memory behind one boundary; your Deep Lake credentials in exactly one place.
Claude Code Cursor Codex Hermes pi OpenClaw
β β β β β β
βββββββββββββ΄βββββ¬βββββ΄βββββββββ΄ββββββββ΄βββββββββ
hooks Β· CLI Β· MCP Β· SDK (thin clients)
β
loopback HTTP Β· 127.0.0.1:3850
β
ββββββββββββββββββββββββββββββββ
β honeycomb daemon β sole storage client
β capture Β· recall Β· skillify β owns your credentials
β pollinate Β· session priming β
βββββββββββββββββ¬βββββββββββββββ
β
ββββββββββββββββββββββββββββββββ
β Activeloop Deep Lake β versioned Β· columnar + vector
β Tier 1 Β· Tier 2 Β· Tier 3 β BM25 + semantic hybrid
ββββββββββββββββββββββββββββββββ
This is the heart of what Legion Code adds on top of Deep Lake. The same memory lives at three levels of detail at once, and the agent chooses how far to zoom:
| Tier | What it is | When it's used |
|---|---|---|
| Tier 1 Β· Key | One keyword-dense sentence per session or fact. The index. | Skimmed at session start during priming. |
| Tier 2 Β· Summary | A distilled recap: goals, decisions, blockers, outcomes. Carries th |