uteke-memory

A persistent memory system for AI agents, accessed through the uteke command-line tool. It can store, recall, search, organize, and remove information, with separate namespaces for different agents.

In plain words
What is it for?
Saving memories, searching them with text or meaning-based queries, grouping knowledge into rooms, and managing agent-specific memory.
Why use it?
It gives agents a place to retain useful information between conversations instead of relying only on the current chat.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/codecoradev/uteke/uteke-memory
Any agent
npx skills add codecoradev/uteke --skill uteke-memory
Clone the repo
git clone --depth 1 https://github.com/codecoradev/uteke

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,490 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00044 $0.03490
Opus 5 $0.00022 $0.01745
Sonnet 5 $0.00009 $0.00698
Haiku 4.5 $0.00004 $0.00349

Measured 2d ago against content hash 4be2a32bb87e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

uteke-memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/uteke-memory/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Uteke Memory Skill

Persistent memory engine for AI agents via the uteke CLI. Version: 0.10.0 — SQLite + usearch HNSW + FTS5 hybrid search (RRF k=60). Zero unsafe code.

Hermes integration: Install the uteke-memory plugin for automatic recall on every turn via the pre_llm_call hook. No shell hook or daemon needed. See extensions/hermes-memory-provider/ for the plugin source. Manual tool calls via uteke-tool plugin remain available for explicit remember/forget/room operations.

Global Flags (all commands)

Flag Description
--store <PATH> Override store path (default: ~/.uteke)
--namespace <NS> Multi-agent isolation (default: "default")
--json Machine-readable JSON output
--verbose Debug logging

Commands

Core Memory Operations

Command Description Key Options
uteke remember <TEXT> Store a new memory --tags, --type, --entity, --category, --meta, --room, --author, --source, --source-type, --detect-contradiction
uteke recall <QUERY> Hybrid search (vector + FTS5, RRF) --limit, --tags, --entity, --category, --min, --strategy (vector/fts5/hybrid/graph), --salience, --recency, --related, --depth, --context, --at (time-travel), --type (all/memory/doc), --where (JSON field filter)
uteke search <QUERY> Keyword text search --limit, --tags
uteke list List memories with filters --tag, --entity, --category, --limit, --offset, --at
uteke get <ID> Get single memory by UUID
uteke forget <ID> Delete memory by ID, tag, tier, or all --tag, --cold, --all, --confirm

Documents (Wiki / Knowledge Base)

Command Description Key Options
uteke doc create <SLUG> Create document from file/stdin --title, --file, --content, --tags, --parent
uteke doc get <ID_OR_SLUG> Get a document
uteke doc update <ID_OR_SLUG> Partial update — only provided fields change --title, --content, --file, --tags, --metadata
uteke doc delete <ID> Delete document (cascades to children)
uteke doc list List documents --limit, --tree (hierarchy)
uteke doc search <QUERY> Search documents (semantic + FTS5) --limit, --mode (semantic/fts/hybrid)
uteke doc children <PARENT> List child documents --limit
uteke doc move <ID_OR_SLUG> Move to new parent or root --parent
uteke doc breadcrumbs <ID_OR_SLUG> Show path from root
uteke doc descendants <ID_OR_SLUG> List all descendants --max-depth, --limit
uteke doc export Export all documents as JSON --output

Read the full file on GitHub · 300 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 300 lines · 44 tokens per session scan A 4be2a32bb87e

Subscribe to this mod's changes

uteke-memory is a skill published in the GitHub repository codecoradev/uteke (235 stars, last pushed 3d ago), licensed Apache-2.0. It adds 44 tokens to every session and 3,490 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

velesdb-memory

Use durable, explainable, self-improving memory across a coding session via the velesdb-memory MCP server. Trigger whenever the velesdb-memory MCP tools (remember/recall/recallfused/relate/why/feedback/forget/rememberextracted/extractionstatus/entity/memorystatus) are available and the work would benefit from…

cyberlife-coder/VelesDB · 328 tokens

velesdb-context-optimizer

Compress an agent's working context deterministically with VelesDB's context compiler before sending it to a model — fewer tokens, same facts, every decision auditable and reversible. Use when a prompt is bloated with repeated context, long logs, or accumulated conversation turns; when token costs need to drop…

cyberlife-coder/VelesDB · 175 tokens

velesdb-learning-loop

Turn every velesdb design / implement / verify cycle into durable, connected memory so the SAME mistake is never repeated and later decisions build on what was already learned, instead of re-deriving it or silently colliding with it. Trigger BEFORE starting a design or implementation on velesdb / velesdb-core /…

cyberlife-coder/VelesDB · 275 tokens

core-parity-audit

Re-run the VelesDB core-vs-ecosystem gap analysis (code + documentation). Use when asked to audit API parity, check that every crate/SDK/integration/doc has caught up to velesdb-core, verify the core↔children architecture is clean, or produce a parity matrix. velesdb-core is the single source of truth; the VelesDB…

cyberlife-coder/VelesDB · 91 tokens

gno

Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…

gmickel/gno · 86 tokens

using-the-skill-librarian

Use when starting any non-trivial task, when wondering "is there a skill for this", or after finishing work that used a librarian recommendation. Applies in every agent connected to the skill-librarian MCP server.

aka-kika/the-librarian · 51 tokens