chatgpt-import

Import ChatGPT conversation history into OpenClaw's memory search. Use when migrating from ChatGPT, giving OpenClaw access to old conversations, or building a searchable archive of past chats.

16 stars

Best use case

chatgpt-import is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Import ChatGPT conversation history into OpenClaw's memory search. Use when migrating from ChatGPT, giving OpenClaw access to old conversations, or building a searchable archive of past chats.

Teams using chatgpt-import should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/chatgpt-import/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/data-ai/chatgpt-import/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/chatgpt-import/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How chatgpt-import Compares

Feature / Agentchatgpt-importStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Import ChatGPT conversation history into OpenClaw's memory search. Use when migrating from ChatGPT, giving OpenClaw access to old conversations, or building a searchable archive of past chats.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# ChatGPT History Import

Import your ChatGPT conversations into OpenClaw so they're searchable via memory search.

## Workflow

### 1. Export from ChatGPT

Follow [references/export-guide.md](references/export-guide.md) to download your `conversations.json`.

### 2. Convert to Markdown

```bash
python3 scripts/convert_chatgpt.py \
  --input /path/to/conversations.json \
  --output /path/to/chatgpt-history
```

Options: `--min-messages N` to skip trivial conversations (default: 2).

### 3. Embed into SQLite

```bash
export OPENAI_API_KEY=sk-...
python3 scripts/bulk_embed.py \
  --history-dir /path/to/chatgpt-history \
  --db /path/to/chatgpt-memory.sqlite
```

Options: `--model`, `--batch-size`, `--max-workers`, `--chunk-size`, `--api-key`.

### 4. Configure OpenClaw

Add as an extra search path in your OpenClaw config:

```yaml
memorySearch:
  extraPaths:
    - /path/to/chatgpt-memory.sqlite
```

Then restart the gateway:

```bash
openclaw gateway restart
```

## Important Notes

- **OpenAI API key required.** The embed script sends conversation text to `api.openai.com` for embedding. If your conversations contain secrets, consider filtering them out first or using a scoped API key.
- **No key material stored.** The generated DB does not store your API key.
- **Back up first.** The embed script will refuse to overwrite an existing output DB.
- **Embeddings cost money** — but it's cheap. ~2,400 conversations cost ~$0.15 with `text-embedding-3-small`.

Related Skills

imports-aliasing

16
from diegosouzapw/awesome-omni-skill

Recommends using aliased imports as defined in svelte.config.js. This improves code organization and readability, especially when dealing with complex project structures.

import-organization

16
from diegosouzapw/awesome-omni-skill

Order imports by: built-in modules, external packages, internal modules, relative imports Use when maintaining consistent code style. Style category skill.

import-existing-ai-config

16
from diegosouzapw/awesome-omni-skill

Import existing AI tool configurations (from Claude, Copilot, or Cursor) into universal-ai-config templates. Converts target-specific files into universal templates.

chatgpt

16
from diegosouzapw/awesome-omni-skill

OpenAI's conversational AI assistant.

chatgpt-exporter-ultimate

16
from diegosouzapw/awesome-omni-skill

Export ALL your ChatGPT conversations instantly — no 24h wait, no extensions. Works via browser relay OR standalone bookmarklet. Extracts full message history with timestamps, roles, and metadata. One command, one JSON file, done.

boycott-chatgpt-54c8dfea

16
from diegosouzapw/awesome-omni-skill

OpenAI president Greg Brockman gave [$25 million](https://www.sfgate.com/tech/article/brockman-openai-top-trump-donor-21273419.php) to MAGA Inc in 2025. They gave Trump 26x more than any other major AI company. ICE's resume screening tool is powered by OpenAI's GPT-4. They're spending 50 million dollars to prevent states from regulating AI.

archetype-import

16
from diegosouzapw/awesome-omni-skill

Imports Shadowrun 5e character archetypes from sourcebook stat blocks into hierarchical markdown and PDF documents with priority inference and data validation. Use when converting official SR5 archetypes to Shadow Master format.

agentuity-cli-cloud-secret-import

16
from diegosouzapw/awesome-omni-skill

Import secrets from a file to cloud and local .env. Requires authentication. Use for Agentuity cloud platform operations

agentuity-cli-cloud-env-import

16
from diegosouzapw/awesome-omni-skill

Import environment variables from a file to cloud and local .env. Requires authentication. Use for Agentuity cloud platform operations

how-to-build-chatgpt-sidebar

16
from diegosouzapw/awesome-omni-skill

Use when asked to build a sidebar experience similar to ChatGPT.com / OpenAI

guard-users-chatgpt

16
from diegosouzapw/awesome-omni-skill

Guardrail policy for Chatgpt CLI: refuse catastrophic actions, require scoped approvals, and reduce secret leakage.

chatgpt / 启用开发者模式的 / openai

16
from diegosouzapw/awesome-omni-skill

General SOP for common requests related to chatgpt, 启用开发者模式的, openai.