Orca CLI
stablyai/orca
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…
Durable cross-session memory: named banks of always-injected markdown rules and auto-extracted memories with hybrid recall.
Install Memory
$ npx skills add iii-hq/workers --skill memory -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install iii-hq/workers memory --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/iii-hq/workers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/memory/skills .claude/skills/memory && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "memory" agent skill from https://github.com/iii-hq/workers/tree/main/memory/skills into .claude/skills/memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/iii-hq/workers/tree/main/memory/skillsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add iii-hq/workers --skill memory -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install iii-hq/workers memory --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/iii-hq/workers.git skills-src && mkdir -p .agents/skills && cp -r skills-src/memory/skills .agents/skills/memory && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "memory" agent skill from https://github.com/iii-hq/workers/tree/main/memory/skills into .agents/skills/memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add iii-hq/workers --skill memory -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install iii-hq/workers memory --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/iii-hq/workers.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/memory/skills .cursor/skills/memory && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "memory" agent skill from https://github.com/iii-hq/workers/tree/main/memory/skills into .cursor/skills/memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/iii-hq/workers.git --path memory/skills--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add iii-hq/workers --skill memory -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install iii-hq/workers memory --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/iii-hq/workers.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/memory/skills .gemini/skills/memory && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "memory" agent skill from https://github.com/iii-hq/workers/tree/main/memory/skills into .gemini/skills/memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install iii-hq/workers memoryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add iii-hq/workers --skill memory -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/iii-hq/workers.git skills-src && mkdir -p .github/skills && cp -r skills-src/memory/skills .github/skills/memory && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "memory" agent skill from https://github.com/iii-hq/workers/tree/main/memory/skills into .github/skills/memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add iii-hq/workers --skill memory -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install iii-hq/workers memory --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/iii-hq/workers.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/memory/skills .opencode/skills/memory && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "memory" agent skill from https://github.com/iii-hq/workers/tree/main/memory/skills into .opencode/skills/memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
memory- GitHub stars
- 113
- Token cost
- ~1.3k tokens
- SKILL.md length
- 641 words
- Files
- 1
- Skills in repo
- 19
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Durable cross-session memory: named banks of always-injected markdown rules and auto-extracted memories with hybrid recall.
- Works in 3 steps: Why bind — memory::item-changed fires on… → When to bind — a UI or index that must… → How to bind — two steps: register a…
- Asks you to remember
- SKILL.md covers When to Use, Boundaries, Functions and Reactive triggers
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Memory is an agent skill from iii-hq/workers. Durable cross-session memory: named banks of always-injected markdown rules and auto-extracted memories with hybrid recall. Reach for it when the user asks you to remember, forget, or inspect what is remembered.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Session handoff. The licence is Apache-2.0.
When your agent uses it
- Asks you to remember
- Inspect what is remembered
Example prompts
- “/memory”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Why bind — memory::item-changed fires on every memory create / update /
- When to bind — a UI or index that must stay current with background
- How to bind — two steps: register a handler function, then register a
What it can do on your machine
Read from SKILL.md and the folder at commit 72ae6ab. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Memory loads about 1.3k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 641 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from iii-hq/workers at commit 72ae6ab, republished under its Apache-2.0 licence (© iii-hq). 641 words, ~1,318 tokens.
Download SKILL.mdSave it as
.claude/skills/memory/SKILL.md (or your agent's skills folder).- name
- memory
- description
- Durable cross-session memory: named banks of always-injected markdown rules and auto-extracted memories with hybrid recall. Reach for it when the user asks you to remember, forget, or inspect what is remembered.
- tags
- memory, banks, rules, recall, cross-session, pinning
memory
Cross-session memory is automatic here. The session's bank injects its rules
and relevant memories into your context each turn, new memories are extracted
in the background after each turn, and standing instructions (style directives,
workflow corrections) graduate into the bank's auto-managed learned rule on
their own. When the user asks you to remember something, acknowledge it — no
save call is required, though an explicit memory::save makes it durable
immediately instead of after the turn.
Rules are markdown documents injected whole into the system prompt on every
turn (memory::rule::*, on disk under the bank's rules/ folder). Memories
are recalled records, ranked against the current question
(memory::save/list/recall). Durable identity-grade guidance belongs in a
rule; point-in-time information belongs in memories.
When to Use
- The user says "remember X", or corrects you in a way that should stick —
save it now:
memory::save { "text": "...", "entities": [...], "pinned": true }. Pin anything they explicitly ask to keep. Re-saving reinforces, never duplicates. - The user asks what you remember about a topic —
memory::recall { "query": "..." }returns the exact ranked memories a turn on that topic would be given. - The user asks to fix or forget something — find it via recall/list, then
memory::update(corrected text) ormemory::delete(tombstone), andmemory::pinto protect the corrected version. - The user wants a style or convention set enforced everywhere —
memory::rule::set { "bank": "...", "name": "style", "content": "..." }. - Separate contexts deserve separate banks (
blogvscoding): a session selects its bank via session metadatamemory_bank(session::set-meta) or the console composer's bank picker;memory::bank::createmakes one. - Memory seems absent —
memory::doctor {}runs a real save→recall roundtrip and names which sibling (router, session-manager) is degraded.
Boundaries
- Not a transcript store: session history lives in session-manager; memory keeps distilled records that point back at their source session.
- Not per-turn context compression: that is context-manager's job. This worker is the durable cross-session sibling.
- Deletes are tombstones and bank deletion moves to
.trash/— nothing is destroyed;include_superseded: trueon list/recall shows history. - Extraction never edits or removes existing memories (ADD-only, fingerprint
reinforced); dedup/merge/promote hygiene belongs to the
memory-consolidatesibling worker. - Injection is bounded (
max_rule_chars,recall_budget_tokens) — an over-budget rule is truncated visibly, never silently dropped.
Show full SKILL.md (292 more words)Show less
Functions
memory::save— explicit save; content-fingerprinted, repeat saves reinforce.memory::get / list / update / delete / pin— memory CRUD; delete tombstones, update bumps a revision, pinned records are untouchable by automatic paths.memory::recall— rank a bank's memories against a query (the injection hook's exact scorer); response names the retrieval mode that ran;tagnarrows to one label.memory::preview— the FULL injection dry-run for a hypothetical chat message: the system-prompt rules section, the memories a turn would be handed (floor + budget applied), and the appended message verbatim.memory::tags— a bank's distinct tags with counts. Addtagson save when the user wants memories organized within a bank.memory::bank::create / list / delete— named memory scopes; delete trashes.memory::rule::list / set— always-injected markdown rules; empty content removes a rule.memory::supersede— retire one memory in favor of another (tombstone + pointer); the consolidation seam, agent-denied by default.memory::doctor— end-to-end self-test plus sibling reachability.memory::reload— re-read every bank from disk after hand-editing files.
Reactive triggers
The worker emits two trigger types; bind to them for live views instead of
polling memory::list / memory::bank::list.
- Why bind —
memory::item-changedfires on every memory create / update / supersede / delete ({ event_type, bank, memory });memory::bank-changedfires on bank create / trash and rule changes ({ event_type, bank }). A consumer that mutates memory already has the new record in its return payload — bind only when you need to observe changes made by OTHERS (extraction, other sessions, the console). - When to bind — a UI or index that must stay current with background
extraction; a worker reacting to new memories in a specific bank (use the
bankfilter in the binding config). - How to bind — two steps: register a handler function, then register a
trigger of the wanted type pointing at it, optionally with
config: { "bank": "blog" }to filter. Delivery is fire-and-forget, at-least-once, unordered.
© iii-hq, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in memory/skills of iii-hq/workers.
Open the folder on GitHubat commit 72ae6ab
Compare with similar skills
Memory next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Memory this skilliii-hq/workers | 113 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Orca CLIstablyai/orca | 87k | 2 repos | ~593 | Automated safety check: Pass | MIT | |
| Coding Agent Session Findercode-yeongyu/oh-my-openagent | 70k | 1 repos | ~2.8k | Automated safety check: Pass | Custom licence | |
| Beads Task Memorygastownhall/beads | 28k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Session History Searchslopus/happy | 24k | — | ~3.1k | Automated safety check: Pass | MIT | |
| Paseo Agent Handoffgetpaseo/paseo | 20k | 1 repos | ~606 | Automated safety check: Pass | Custom licence |
Similar skills
Coding Agent Session Finder
code-yeongyu/oh-my-openagent
Finds, reads and reconstructs past coding-agent sessions across Codex, Claude, OpenCode, Senpi and many other local agent logs.
Beads Task Memory
gastownhall/beads
Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.
Session History Search
slopus/happy
Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.
Paseo Agent Handoff
getpaseo/paseo
Hands off the current task, including context, decisions and failed attempts, to a fresh agent through Paseo by writing a self-contained briefing prompt and launching that agent.
Memori Long-Term Memory
MemoriLabs/Memori
Connects Claude Code to Memori Cloud for long-term memory, recalling stored context before substantive replies and saving new context afterward.
More from iii-hq/workers
All 19 skills in this repoCron
iii-hq/workers
Schedule any registered function on a 6- or 7-field cron expression with the standalone cron worker.
Email
iii-hq/workers
Send and read email from the iii engine — SMTP send, IMAP read, and real-time IDLE push as a subscribable trigger type.
HTTP
iii-hq/workers
Expose registered functions as HTTP endpoints with the standalone http worker.
Kanban
iii-hq/workers
File-backed kanban board: create, read, move and comment on tickets by key or uuid, assign agent profiles, and wake on comments through the kanban:comment trigger instead of polling.
Pubsub
iii-hq/workers
Fire-and-forget topic pub/sub: broadcast an event with publish and every matching subscribe trigger receives it.
Release Sync
iii-hq/workers
Organize worker release tags into Linear release waves — one team document plus one release/<date label per same-day batch of worker releases, with shipped MOT issues labeled and linked.
Related
Categories
Questions about Memory
What does Memory do?
Durable cross-session memory: named banks of always-injected markdown rules and auto-extracted memories with hybrid recall. Memory is an agent skill from iii-hq/workers. Durable cross-session memory: named banks of always-injected markdown rules and auto-extracted memories with hybrid recall.
When should I use Memory?
Memory fits situations like: asks you to remember; inspect what is remembered.
How do I install Memory in Claude Code?
Run `npx skills add iii-hq/workers --skill memory -a claude-code`. Or copy the skill folder (memory/skills in iii-hq/workers) into .claude/skills/memory in your project. Claude Code loads it when a task matches its description.
How do I install Memory in Codex?
Run `npx skills add iii-hq/workers --skill memory -a codex`. Or copy the skill folder (memory/skills in iii-hq/workers) into .agents/skills/memory in your project. Codex loads it when a task matches its description.
Can I use Memory in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add iii-hq/workers --skill memory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memory, .gemini/skills/memory, .github/skills/memory and .opencode/skills/memory in your project.
What does Memory need to run?
SKILL.md names no scripts, command-line tools or credentials: Memory is instructions for the agent only.
Does Memory access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Memory safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Memory use?
Memory is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Memory use?
About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Memory?
Skills that share tags, products or a category with Memory: Orca CLI (stablyai/orca, 87k stars), Coding Agent Session Finder (code-yeongyu/oh-my-openagent, 70k stars), Beads Task Memory (gastownhall/beads, 28k stars) and Session History Search (slopus/happy, 24k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Memory?
iii-hq (a GitHub organization) maintains it in iii-hq/workers, which has 113 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 8, 2026.
Source: iii-hq/workers on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.