New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Cognee Memory Recall

by topoteretes in topoteretes/cognee

Explains how to query cognee agent memory with recall(): how the search type is chosen, how to narrow a query to datasets, and what the returned results contain.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Cognee Memory Recall

skills CLI
$ npx skills add topoteretes/cognee --skill cognee-recall -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install topoteretes/cognee cognee-recall --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/topoteretes/cognee.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cognee-recall .claude/skills/cognee-recall && rm -rf skills-src

Use ~/.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/

Facts

Skill name
cognee-recall
GitHub stars
32k
Token cost
~2.6k tokens
SKILL.md length
1,176 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
Apache-2.0

At a glance

Explains how to query cognee agent memory with recall(): how the search type is chosen, how to narrow a query to datasets, and what the returned results contain.

  • Works in 4 steps: An explicit query_type=SearchType.X… → Otherwise, with no usable LLM key,… → Otherwise the router (auto_route=True,… → …
  • Choosing between graph, chunk and hybrid search when querying cognee memory
  • SKILL.md covers Use it, Pitfalls, recall() or search()? and How it works, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill documents cognee's recall() call, which searches the memory graph and, when a session is supplied, the session cache, then returns a list of tagged results. With no datasets argument it searches every dataset the user may read. Passing dataset names, or UUIDs that take priority, narrows the search and makes it faster.

It spells out how the search type is selected. An explicit query_type always wins, a missing LLM key falls back to plain vector search over chunks, and otherwise a router with two regex rules picks between exact-phrase lexical search and coding rules, defaulting to hybrid completion. A table lists each search type, whether it calls an LLM and what it suits, from graph completion and temporal questions to summaries and skill lookup. The description also covers node sets, sessions, getting context or citations instead of an answer, and debugging empty results.

When your agent uses it

  • Choosing between graph, chunk and hybrid search when querying cognee memory
  • Limiting a recall query to one dataset or to a single session
  • Finding out why a cognee query returns nothing or something unexpected

Example prompts

  • “Query my cognee memory for what changed in v2, and force graph completion as the search type.”
  • “Search only the research dataset in cognee for where Einstein was born.”
  • “Why does cognee.recall return an empty list for this user even though the data was added?”

Requirements

  • Python with the cognee package
  • An LLM API key for the search types that call a model

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. An explicit query_type=SearchType.X always wins.
  2. Otherwise, with no usable LLM key, CHUNKS (plain vector search).
  3. Otherwise the router (auto_route=True, the default). It is two regex
  4. Everything else → HYBRID_COMPLETION.

What it can do on your machine

Read from SKILL.md and the folder at commit 0ec7a9f. 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 (its code samples are python).

    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

Cognee Memory Recall loads about 2.6k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 1,176 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

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 topoteretes/cognee at commit 0ec7a9f, republished under its Apache-2.0 licence (© topoteretes). 1,176 words, ~2,646 tokens.

Download SKILL.mdSave it as .claude/skills/cognee-recall/SKILL.md (or your agent's skills folder).
name
cognee-recall
description
Use when querying cognee memory with recall() (or search()) — picking a search type, understanding auto-routing, scoping to datasets, node sets or sessions, getting context or citations instead of an answer, reading the results, or debugging empty or unexpected results.

Query memory with recall()

recall() is cognee's query API. It picks a search strategy, searches the graph and (with a session) the session cache, and returns a list of tagged results.

python
import cognee

results = await cognee.recall("Where was Einstein born?")
for r in results:
    print(r.source, r.text)  # e.g. "graph", "Einstein was born in Ulm."

Without datasets it searches every dataset the user can read. Pass datasets=["research"] (names) or dataset_ids=[...] (UUIDs, which win) to narrow it; that is also faster.

Use it

How the search type is picked
  1. An explicit query_type=SearchType.X always wins.
  2. Otherwise, with no usable LLM key, CHUNKS (plain vector search).
  3. Otherwise the router (auto_route=True, the default). It is two regex rules, first match wins, no LLM call:
    • the whole query is one "quoted phrase" → CHUNKS_LEXICAL
    • mentions coding rules/standards/conventions or code-review guidelines → CODING_RULES
  4. Everything else → HYBRID_COMPLETION.

A routed type (never a pinned one) that the backend rejects, or a routed CHUNKS_LEXICAL / CODING_RULES that returns nothing, is retried once as HYBRID_COMPLETION. The router never picks CYPHER.

python
from cognee import SearchType

await cognee.recall("What changed in v2?", query_type=SearchType.GRAPH_COMPLETION)
Search types

The full list is cognee/modules/search/types/SearchType.py; the type-to-retriever table is cognee/modules/retrieval/README.md.

TypeLLM?Use for
HYBRID_COMPLETION (default)yesGeneral questions: document passages plus entity neighbourhoods, then an answer
GRAPH_COMPLETIONyesAnswers from graph relationships
GRAPH_COMPLETION_COT, _CONTEXT_EXTENSION, _DECOMPOSITIONyesHarder multi-hop questions (more LLM calls)
GRAPH_SUMMARY_COMPLETIONyesSummarizes the retrieved graph edges at query time (extra LLM call), then answers
RAG_COMPLETIONyesClassic chunk RAG
TRIPLET_COMPLETIONyesSubject-predicate-object facts (needs triplet embedding)
TEMPORALyesTime questions; reads the Timestamp nodes the default pipeline extracts
CHUNKSnoRaw passages by vector similarity
CHUNKS_LEXICALnoKeyword / exact-phrase match
SUMMARIESnoDocument summaries
CODEnoCode-graph operations via code_query={...}; needs scope="code" in recall
SKILLSnoDiscover skill playbooks; exactly one dataset
CYPHERnoRaw Cypher. On by default; ALLOW_CYPHER_QUERY=false disables it. It can write, so only pass user-authored queries deliberately
NATURAL_LANGUAGEyesLLM writes Cypher, then runs it (same flag)
GRAPH_REPORTpartlyGraph insight report: hubs, cross-set links, suggested questions
FEELING_LUCKYyesAn LLM picks the type
AGENTIC_COMPLETIONyesMulti-step loop with skills/tools; exactly one dataset. Use search() for its parameters
Scope: which sources are searched

scope is one of, or a list of: graph, session, session_first, trace, session_context, all, tools, code. all means graph + session + trace + session_context; tools and code are never included implicitly.

When scope is omitted:

You passSources
session_id onlySession first; a session hit skips the graph
session_id + datasetsSession and graph both contribute
session_id + query_typeGraph only — pinning a type drops the session
no session_idGraph only

Session and trace search is keyword overlap, not embeddings.

Filters and knobs
  • top_k=15: per dataset, not in total. The default HYBRID caps each lane at min(top_k, 10); set chunks_top_k / entities_top_k / facts_top_k in retriever_specific_config to go higher.
  • node_name=["AI"] (+ node_name_filter_operator="OR"|"AND"): restricts graph/chunk/completion types to data remembered with that node_set. SUMMARIES, CHUNKS_LEXICAL, GRAPH_REPORT, CYPHER, NATURAL_LANGUAGE, CODE and SKILLS ignore it; CODING_RULES treats it as the rules node-set name.
  • system_prompt / system_prompt_path: change the answering prompt.
  • response_model=MyPydanticModel: structured answer, on r.structured.
  • include_references=True: attach the document chunks that support each graph edge used (needs EDGE_EVIDENCE_ENABLED=true, the default).
  • only_context=True: return what the LLM would have received instead of an answer. r.text is the rendered user prompt, r.system_prompt the system prompt. Pin query_type when you use it.
  • retriever_specific_config={...}: retriever-only options. For the agentic extras (skills, tools, max_iter) and node_type, call cognee.search() instead, which takes them as parameters.
Reading the results

Each item is a Pydantic model with a source discriminator: graph, session, trace, session_context, code, tools, skills, or system. Graph items carry text (always renderable), search_type, kind, score, dataset_id / dataset_name, metadata, raw, and structured. A system item is a status marker, not data (see "memory warming up" below).

When a query sounds procedural ("how do I…", "runbook", "steps to…") and exactly one dataset is targeted, recall also runs a small SKILLS lookup and appends hits with source="skills". Disable with SKILL_GATE_ENABLED=false.

Show full SKILL.md (557 more words)Show less

Pitfalls

  • Permissions change what you get back. With no datasets, recall searches only datasets the user can read, so a user without grants gets one source="system" memory_warming_up marker from a graph-only recall (with only_context=True or RECALL_WARMUP_SHORTCIRCUIT=false it gets []; with session sources included only the graph lane is empty, and session and trace hits still come back). Asking for a dataset id the user cannot read raises PermissionDeniedError (HTTP 403). Dataset names resolve only among the user's own datasets, so a name that is not theirs (even one shared with them) raises DatasetNotFoundError; use dataset_ids for shared datasets. See the cognee-permissions skill.
  • "Memory warming up". On an empty graph, a graph-only recall (no session sources, not only_context) returns one source="system" item with status="memory_warming_up" (or "build_failed" plus error_message) instead of results; a multi-source recall just returns no graph results. Wait for the remember to finish, or check why it failed.
  • Hybrid silently becomes graph completion when you pass neighborhood_depth or feedback_influence > 0 (including a nonzero DEFAULT_FEEDBACK_INFLUENCE), or the chunk collection is missing. node_name stays on hybrid, which filters to that node set. search() also defers for a custom node_type or node_name with node_type=None; recall() has no node_type. wide_search_top_k and triplet_distance_penalty with hybrid raise InvalidHybridSearchConfig; pin GRAPH_COMPLETION to use them.
  • SKILLS and AGENTIC_COMPLETION need exactly one dataset. For SKILLS, search() raises unless exactly one dataset is given. recall() runs SKILLS per dataset with access control on (zero datasets gives [], not an error) and raises only with access control off and not exactly one dataset. For AGENTIC_COMPLETION only search() checks it up front, so call it through search() with one dataset.
  • code_query without scope="code" raises, and scope="tools" also needs TOOL_CALLS_ENABLED=true.
  • Latency. Most completion types make one LLM call; COT, DECOMPOSITION, CONTEXT_EXTENSION, GRAPH_SUMMARY_COMPLETION, TEMPORAL, FEELING_LUCKY (one call to pick the type, then the chosen type's) and AGENTIC_COMPLETION (a loop of up to max_iter, default 6) make more. NATURAL_LANGUAGE makes one (no answer call) and retries only on an empty or failed query, up to 3 attempts. With CACHING and AUTO_FEEDBACK on (defaults), each answered turn adds one analysis call, even without a session_id. Set AUTO_FEEDBACK=false for low-latency reads (see the cognee-performance skill).

Use recall(). Drop to cognee.search() only for agentic parameters (skills, tools, max_iter, node_type) as first-class arguments, raw SearchResult objects, or a pinned type with no router. search() never searches the session cache; its session_id only adds conversation history to the prompt. Full guide: docs/recall-vs-search.md.

How it works

recall() resolves scope and search type, then calls the same authorized search search() uses: datasets resolve through the permission layer with read, one search per dataset runs concurrently, and results are normalized and tagged.

  • Entry point, scope and type resolution: cognee/api/v1/recall/recall.py
  • Router: cognee/api/v1/recall/query_router.py
  • Skill gate: cognee/api/v1/recall/skill_gate.py
  • Result types: cognee/modules/recall/types/RecallResponse.py, SearchResultItem.py
  • Scope names: cognee/memory/entries.py:normalize_scope
  • Warm-up config (RECALL_WARMUP_*): cognee/modules/recall/config.py
  • Core search and fan-out: cognee/modules/search/methods/search.py
  • Hybrid fallback rules: cognee/modules/search/methods/hybrid_deferral.py
  • Registry: cognee/modules/search/methods/get_search_type_retriever_instance.py

Examples in examples/guides/: recall_core.py, hybrid_retrieval_recall.py, references_example.py, temporal_recall.py, sessions.py.

Extending it

Adding a search type, per cognee/modules/retrieval/README.md:

  1. Write the retriever in cognee/modules/retrieval/ (subclass BaseRetriever or a completion base).
  2. Add the SearchType member and its search_core_registry entry.
  3. Add a row to the README table. A unit test (cognee/tests/unit/modules/retrieval/retriever_readme_index_test.py) fails if the table and registry disagree.
  4. Optional: add it to SEARCH_TYPE_CHOICES in cognee/cli/config.py for the CLI, or a regex rule to query_router.py for auto-routing. Never route a type that can write.

© topoteretes, 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 .agents/skills/cognee-recall of topoteretes/cognee.

Open the folder on GitHubat commit 0ec7a9f

Compare with similar skills

Cognee Memory Recall 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.

Cognee Memory Recall compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cognee Memory Recall this skilltopoteretes/cognee32k—~2.6kAutomated safety check: PassApache-2.0
Cortexdb Memory Hermesliliang-cn/cortexdb274—~1.7kAutomated safety check: PassMIT
Neo4j Graphrag Skillneo4j-contrib/neo4j-skills114—~4.2kAutomated safety check: NotesMIT
Cortexdb Memory Openclawliliang-cn/cortexdb274—~1.6kAutomated safety check: PassMIT
Hermes Memory Providersmnemosyne-oss/mnemosyne3.4k—~1.8kAutomated safety check: PassMIT
Compact Memory Implementationsimbajigege/book2skills183—~2.5kAutomated safety check: PassMIT

Similar skills

  • Cortexdb Memory Hermes

    liliang-cn/cortexdb

    Give a Python agent (such as Hermes Agent by Nous Research) durable, local-first memory plus a queryable SPARQL knowledge graph, backed by CortexDB through its gRPC sidecar and the cortexdb-client…

    274 GitHub stars~1.7k tokensUpdated 3 days ago
    Knowledge ManagementAuto-check passed

  • Neo4j Graphrag Skill

    neo4j-contrib/neo4j-skills

    Build GraphRAG retrieval pipelines on Neo4j using the neo4j-graphrag Python package (v1.22.0+).

    114 GitHub stars~4.2k tokensUpdated yesterday
    Knowledge ManagementAuto-check: notes

  • Cortexdb Memory Openclaw

    liliang-cn/cortexdb

    Give a Node.js agent (such as OpenClaw) durable, local-first memory plus a queryable SPARQL knowledge graph, backed by CortexDB through its gRPC sidecar and the cortexdb-client npm package.

    274 GitHub stars~1.6k tokensUpdated 3 days ago
    Knowledge ManagementAuto-check passed

  • Hermes Memory Providers

    mnemosyne-oss/mnemosyne

    Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.

    3.4k GitHub stars~1.8k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Compact Memory Implementation

    simbajigege/book2skills

    A developer guide to adding compact memory to an agent: when to trigger compaction, how to fork a compactor sub-agent, what the summary holds, and how to restore it.

    183 GitHub stars~2.5k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • Deep Agents Core

    langchain-ai/langchain-skills

    Official

    Explains how to build agents with the Deep Agents framework: create_deep_agent, the built-in middleware, the harness, SKILL.md format and configuration options.

    1.3k GitHub stars~3.1k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

More from topoteretes/cognee

All 19 skills in this repo

  • Cognee CLI Memory Commands

    topoteretes/cognee

    Drives cognee from the terminal with remember, recall, forget and improve memory commands, dataset and config management and database migrations.

    32k GitHub stars~2.2k tokensUpdated yesterday
    Auto-check: notes

  • Cognee Community Packages

    topoteretes/cognee

    Guide to using and contributing cognee community packages: database adapters, data-source connectors, custom tasks and retrievers, and Keywords AI observability.

    32k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

  • Cognee Custom Graph Models

    topoteretes/cognee

    Defines the shape of cognee's knowledge graph with graph_model: DataPoint node classes, identity and index fields, typed edges and fixes for duplicated nodes.

    32k GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed

  • Cognee Custom Pipelines

    topoteretes/cognee

    Shows how to write custom cognee tasks, chain them into pipelines, store custom DataPoints and run enrichment over the existing graph.

    32k GitHub stars~2.8k tokensUpdated yesterday
    Auto-check passed

  • Cognee Docker Setup

    topoteretes/cognee

    Runs the Cognee AI memory platform in Docker, from a one-file prebuilt image to a full compose stack with UI, MCP server, Postgres and Neo4j.

    32k GitHub stars~901 tokensUpdated yesterday
    Auto-check: notes

  • Cognee Forget

    topoteretes/cognee

    Removes data from cognee memory with forget(), finding the right dataset and document first and choosing between one document, a dataset or only the graph and vector memory.

    32k GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Cognee Memory Recall

What does Cognee Memory Recall do?

Explains how to query cognee agent memory with recall(): how the search type is chosen, how to narrow a query to datasets, and what the returned results contain. The skill documents cognee's recall() call, which searches the memory graph and, when a session is supplied, the session cache, then returns a list of tagged results. With no datasets argument it searches every dataset the user may read.

When should I use Cognee Memory Recall?

Cognee Memory Recall fits situations like: choosing between graph, chunk and hybrid search when querying cognee memory; limiting a recall query to one dataset or to a single session; finding out why a cognee query returns nothing or something unexpected.

How do I install Cognee Memory Recall in Claude Code?

Run `npx skills add topoteretes/cognee --skill cognee-recall -a claude-code`. Or copy the skill folder (.agents/skills/cognee-recall in topoteretes/cognee) into .claude/skills/cognee-recall in your project. Claude Code loads it when a task matches its description.

How do I install Cognee Memory Recall in Codex?

Run `npx skills add topoteretes/cognee --skill cognee-recall -a codex`. Or copy the skill folder (.agents/skills/cognee-recall in topoteretes/cognee) into .agents/skills/cognee-recall in your project. Codex loads it when a task matches its description.

Can I use Cognee Memory Recall 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 topoteretes/cognee --skill cognee-recall -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cognee-recall, .gemini/skills/cognee-recall, .github/skills/cognee-recall and .opencode/skills/cognee-recall in your project.

What does Cognee Memory Recall need to run?

SKILL.md names no scripts, command-line tools or credentials: Cognee Memory Recall is instructions for the agent only. Our summary lists: Python with the cognee package; An LLM API key for the search types that call a model.

Does Cognee Memory Recall 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 Cognee Memory Recall 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 Cognee Memory Recall use?

Cognee Memory Recall 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 Cognee Memory Recall use?

About 2.6k tokens (SKILL.md is roughly 11k 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 Cognee Memory Recall?

Skills that share tags, products or a category with Cognee Memory Recall: Cortexdb Memory Hermes (liliang-cn/cortexdb, 274 stars), Neo4j Graphrag Skill (neo4j-contrib/neo4j-skills, 114 stars), Cortexdb Memory Openclaw (liliang-cn/cortexdb, 274 stars) and Hermes Memory Providers (mnemosyne-oss/mnemosyne, 3.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cognee Memory Recall?

topoteretes (a GitHub organization) maintains it in topoteretes/cognee, which has 31,919 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 9, 2026.

Source: topoteretes/cognee on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.