Cognee Integrations Setup
topoteretes/cognee
Switches cognee's LLM, embedding, relational, vector and graph backends through environment variables, with the extras to install and the traps to avoid.
Walks through installing and tuning memory-lancedb-pro, picking an embedding, reranker, and LLM combination from four preset configuration plans.
Install LanceDB Memory Configuration Guide
$ npx skills add CortexReach/memory-lancedb-pro-skill --skill memory-lancedb-pro -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install CortexReach/memory-lancedb-pro-skill memory-lancedb-pro --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "memory-lancedb-pro" agent skill from https://github.com/CortexReach/memory-lancedb-pro-skill/tree/main into .claude/skills/memory-lancedb-pro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-lancedb-pro", 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.
$ npx skills add CortexReach/memory-lancedb-pro-skill --skill memory-lancedb-pro -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install CortexReach/memory-lancedb-pro-skill memory-lancedb-pro --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "memory-lancedb-pro" agent skill from https://github.com/CortexReach/memory-lancedb-pro-skill/tree/main into .agents/skills/memory-lancedb-pro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-lancedb-pro", 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 CortexReach/memory-lancedb-pro-skill --skill memory-lancedb-pro -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install CortexReach/memory-lancedb-pro-skill memory-lancedb-pro --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "memory-lancedb-pro" agent skill from https://github.com/CortexReach/memory-lancedb-pro-skill/tree/main into .cursor/skills/memory-lancedb-pro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-lancedb-pro", 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.
$ npx skills add CortexReach/memory-lancedb-pro-skill --skill memory-lancedb-pro -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install CortexReach/memory-lancedb-pro-skill memory-lancedb-pro --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "memory-lancedb-pro" agent skill from https://github.com/CortexReach/memory-lancedb-pro-skill/tree/main into .gemini/skills/memory-lancedb-pro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-lancedb-pro", 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 CortexReach/memory-lancedb-pro-skill memory-lancedb-proInstalls 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 CortexReach/memory-lancedb-pro-skill --skill memory-lancedb-pro -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "memory-lancedb-pro" agent skill from https://github.com/CortexReach/memory-lancedb-pro-skill/tree/main into .github/skills/memory-lancedb-pro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-lancedb-pro", 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 CortexReach/memory-lancedb-pro-skill --skill memory-lancedb-pro -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install CortexReach/memory-lancedb-pro-skill memory-lancedb-pro --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "memory-lancedb-pro" agent skill from https://github.com/CortexReach/memory-lancedb-pro-skill/tree/main into .opencode/skills/memory-lancedb-pro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-lancedb-pro", 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-lancedb-pro- GitHub stars
- 229
- Token cost
- ~14k tokens
- SKILL.md length
- 4,185 words
- Files
- 4 (incl. references, assets)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- None found
At a glance
Walks through installing and tuning memory-lancedb-pro, picking an embedding, reranker, and LLM combination from four preset configuration plans.
- Works in 8 steps: Present configuration plans and let user… → Verify API Keys (MANDATORY — do not skip) → Find openclaw.json → …
- Installing or configuring memory-lancedb-pro for the first time
- SKILL.md covers Applying the Optimal Config…, Installation, Troubleshooting — Error… and Configuration, plus 1 more section
- Calls ollama, curl and rg; reaches api.jina.ai and api.openai.com; needs OPENAI_API_KEY and JINA_API_KEY
What it does
This skill presents four plans to choose from when the user asks for the best or optimal setup: a full-power plan pairing a Jina embedding and reranker with an OpenAI model, a budget plan swapping in a free SiliconFlow reranker, a simple OpenAI-only plan with no reranker, and a fully local Ollama plan with no API keys and no cross-encoder reranker, each listing exactly which API keys it needs and where to get them.
Underneath these plans sits a persistent memory store using LanceDB with hybrid vector-plus-BM25 retrieval, LLM-powered extraction of what to remember, and a Weibull decay lifecycle that ages memories out over time, exposed through memory tools for recall, store, update, forget, listing, and stats, plus self-improvement tools for logging, extracting, and reviewing skills. Full thresholds and schema details live in a separate reference file.
When your agent uses it
- Installing or configuring memory-lancedb-pro for the first time
- Choosing an embedding, reranker, and LLM combination for memory retrieval
- Using the memory recall, store, or self-improvement tools
Example prompts
- “Help me enable the best memory-lancedb-pro configuration.”
- “Set up memory-lancedb-pro fully local with Ollama, no API keys.”
- “Recall what we decided about this project last week.”
Requirements
- An OpenAI, Jina, SiliconFlow, or Ollama key depending on the chosen plan
Workflow steps
8 steps, taken from the step headings in SKILL.md.
- Present configuration plans and let user choose
- Verify API Keys (MANDATORY — do not skip)
- Find openclaw.json
- Read current config
- Build the merged config based on chosen plan
- Apply the config
- Validate and restart
- Verify
What it can do on your machine
Read from SKILL.md and the folder at commit 51eb26d. 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
Shell commands in SKILL.md call:
ollamacurlrggitnodebashnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
api.jina.aiapi.openai.comgithub.comapi.siliconflow.comdashscope.aliyuncs.comgenerativelanguage.googleapis.comraw.githubusercontent.comapi.voyageai.comapi.pinecone.io
Also links to:
platform.openai.comjina.aicloud.siliconflow.cnollama.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
OPENAI_API_KEYJINA_API_KEYSILICONFLOW_API_KEYDASHSCOPE_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
LanceDB Memory Configuration Guide loads about 14k tokens when it runs, and up to ~17k if it reads all its reference files. Until then it costs about 137 tokens; SKILL.md has 4,185 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
Without a licence we can't republish the file, so here is its outline and opening line. It has 4,185 words (~14,350 tokens).
“Production-grade long-term memory system (v1.1.0-beta.8) for OpenClaw AI agents. Provides persistent, intelligent memory storage using LanceDB with hybrid vector + BM25 retrieval, LLM-powered Smart Extraction, Weibull decay lifecycle, and multi-scope isolation.”
- name
- memory-lancedb-pro
Files
SKILL.md and 3 other files (references, assets) in the repository root of CortexReach/memory-lancedb-pro-skill.
- SKILL.md
- README.md
- assets/wechat-qrcode.jpeg
- references/full-reference.md
Open the folder on GitHubat commit 51eb26d
Compare with similar skills
LanceDB Memory Configuration Guide 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 |
|---|---|---|---|---|---|---|
| LanceDB Memory Configuration Guide this skillCortexReach/memory-lancedb-pro-skill | 229 | — | ~14k | Automated safety check: Pass | None | |
| Cognee Integrations Setuptopoteretes/cognee | 32k | — | ~1k | Automated safety check: Notes | Apache-2.0 | |
| Agent RecallGoldentrii/AgentRecall-X | 371 | — | ~5.2k | Automated safety check: Notes | MIT | |
| Codebase Managementgiancarloerra/SocratiCode | 3.3k | 1 repos | ~1.8k | Automated safety check: Pass | AGPL-3.0 | |
| HegelionHmbown/Hegelion | 173 | — | ~359 | Automated safety check: Pass | MIT | |
| Memoryharperreed/dotfiles | 334 | — | ~484 | Automated safety check: Pass | None |
Similar skills
Agent Recall
Goldentrii/AgentRecall-X
Persistent compounding memory for AI agents. An agent skill from Goldentrii/AgentRecall-X.
Codebase Management
giancarloerra/SocratiCode
Set up, index, and manage SocratiCode codebase indexing. An agent skill from giancarloerra/SocratiCode.
Hegelion
Hmbown/Hegelion
Dialectical reasoning and autocoding via Hegelion MCP tools.
Memory
harperreed/dotfiles
Semantic memory and context - store and retrieve information with embeddings for similarity search.
Memory Lancedb Pro Openclaw
LeoYeAI/openclaw-master-skills
Expert skill for memory-lancedb-pro — a production-grade LanceDB-backed long-term memory plugin for OpenClaw agents with hybrid retrieval, cross-encoder reranking, multi-scope isolation, and smart…
Related
Works with
Categories
Questions about LanceDB Memory Configuration Guide
What does LanceDB Memory Configuration Guide do?
Walks through installing and tuning memory-lancedb-pro, picking an embedding, reranker, and LLM combination from four preset configuration plans. This skill presents four plans to choose from when the user asks for the best or optimal setup: a full-power plan pairing a Jina embedding and reranker with an OpenAI model, a budget plan swapping in a free SiliconFlow reranker, a simple OpenAI-only plan with no reranker, and a fully local Ollama plan with no API keys and no cross-encoder reranker, each listing exactly which API keys it needs and where to get them.
When should I use LanceDB Memory Configuration Guide?
LanceDB Memory Configuration Guide fits situations like: installing or configuring memory-lancedb-pro for the first time; choosing an embedding, reranker, and LLM combination for memory retrieval; using the memory recall, store, or self-improvement tools.
How do I install LanceDB Memory Configuration Guide in Claude Code?
Run `npx skills add CortexReach/memory-lancedb-pro-skill --skill memory-lancedb-pro -a claude-code`. Or copy the skill folder (the CortexReach/memory-lancedb-pro-skill repository) into .claude/skills/memory-lancedb-pro in your project. Claude Code loads it when a task matches its description.
How do I install LanceDB Memory Configuration Guide in Codex?
Run `npx skills add CortexReach/memory-lancedb-pro-skill --skill memory-lancedb-pro -a codex`. Or copy the skill folder (the CortexReach/memory-lancedb-pro-skill repository) into .agents/skills/memory-lancedb-pro in your project. Codex loads it when a task matches its description.
Can I use LanceDB Memory Configuration Guide 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 CortexReach/memory-lancedb-pro-skill --skill memory-lancedb-pro -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-lancedb-pro, .gemini/skills/memory-lancedb-pro, .github/skills/memory-lancedb-pro and .opencode/skills/memory-lancedb-pro in your project.
What does LanceDB Memory Configuration Guide need to run?
Going by SKILL.md and its folder, LanceDB Memory Configuration Guide needs the command-line tools its instructions call (ollama, curl, rg, git, node and bash) and credentials named OPENAI_API_KEY, JINA_API_KEY, SILICONFLOW_API_KEY and DASHSCOPE_API_KEY. Our summary lists: An OpenAI, Jina, SiliconFlow, or Ollama key depending on the chosen plan.
Does LanceDB Memory Configuration Guide access the network?
SKILL.md names 13 domains. In commands or code: api.jina.ai, api.openai.com, github.com, api.siliconflow.com, dashscope.aliyuncs.com, generativelanguage.googleapis.com, raw.githubusercontent.com, api.voyageai.com and api.pinecone.io; the agent is likely to contact these when it follows the instructions. As links in the text: platform.openai.com, jina.ai, cloud.siliconflow.cn and ollama.com. This is read from the text; nothing was executed.
Is LanceDB Memory Configuration Guide 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 LanceDB Memory Configuration Guide use?
No licence was found for LanceDB Memory Configuration Guide or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does LanceDB Memory Configuration Guide use?
About 14k tokens (SKILL.md is roughly 57k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.5k tokens, read only when the agent opens those files.
What are the alternatives to LanceDB Memory Configuration Guide?
Skills that share tags, products or a category with LanceDB Memory Configuration Guide: Cognee Integrations Setup (topoteretes/cognee, 32k stars), Agent Recall (Goldentrii/AgentRecall-X, 371 stars), Codebase Management (giancarloerra/SocratiCode, 3.3k stars) and Hegelion (Hmbown/Hegelion, 173 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains LanceDB Memory Configuration Guide?
CortexReach (a GitHub organization) maintains it in CortexReach/memory-lancedb-pro-skill, which has 229 GitHub stars. The repository was last updated on March 22, 2026.
Source: CortexReach/memory-lancedb-pro-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.