← Back to Skills Marketplace
punithg

memic

by Punith · GitHub ↗ · v1.0.4
cross-platform ✓ Security Clean
365
Downloads
2
Stars
1
Active Installs
5
Versions
Install in OpenClaw
/install memic
Description
Context engineering platform for AI agents. Upload documents, search with semantic + structured queries, and inject relevant context into LLM prompts. Suppor...
Usage Guidance
This skill appears coherent for integrating the Memic SDK. Before installing, consider: (1) the MEMIC_API_KEY grants Memic access to searches/uploads — treat it like any API secret; (2) uploading local files or agent session logs to Memic will send data off‑host, so avoid uploading sensitive files unless your data governance permits it; (3) database connectors require you to provide DB credentials to the Memic platform (done via their dashboard), so review access scope and retention policies. If you need an offline/local-only RAG pipeline, this managed SDK may not meet that requirement.
Capability Analysis
Type: OpenClaw Skill Name: memic Version: 1.0.4 The skill bundle is a legitimate integration for the Memic context engineering platform, providing documentation and examples for its Python SDK. The files (SKILL.md, examples.md) describe standard RAG and Text2SQL operations, including file uploads and semantic search, without any evidence of data exfiltration, malicious execution, or prompt injection attacks. All external references point to the official domain https://app.memic.ai.
Capability Assessment
Purpose & Capability
Name/description (context engineering, RAG, Text2SQL) match the declared requirements: pip for installing the Python SDK and MEMIC_API_KEY as the primary credential. Nothing requested appears unrelated to the stated purpose.
Instruction Scope
Runtime instructions show normal SDK usage (install, set MEMIC_API_KEY, upload files, search). This necessarily allows uploading local files and connecting DB connectors via the Memic dashboard (which requires you to provide DB connection details to the service). The SKILL.md also mentions future support for uploading session logs (e.g., MEMORY.md); that capability could expose sensitive agent/session data if used, but it is described as an opt‑in feature rather than an automatic action.
Install Mechanism
This is an instruction‑only skill with no install spec or bundled code. It requires pip on the host so the user can pip install the memic package — expected for a Python SDK. No downloads from untrusted URLs are present.
Credentials
Only MEMIC_API_KEY (primary credential) is required. That matches the SDK's need to authenticate to the managed Memic service. No unrelated secrets or multiple credentials are requested.
Persistence & Privilege
always is false and the skill is user‑invocable; no elevated or persistent privileges are requested. The skill does not instruct modification of other skills or system-wide settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install memic
  3. After installation, invoke the skill by name or use /memic
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.4
- No code or documentation changes in this release. - Metadata updated: the install requirement was changed from the "python3" binary to "pip". - All functionality and usage remain unchanged from the previous version.
v1.0.3
- Version bump: updated skill version from 1.0.0 to 0.3.0 in the manifest. - No code or documentation content changes detected. - No file changes present in this release.
v1.0.2
- Added SKILL metadata block for increased platform compatibility and install requirements. - Declared the version field (now explicitly listed as 1.0.0) and added homepage URL in the SKILL.md. - No code or feature changes to the skill logic; documentation remains unchanged except for the metadata additions.
v1.0.1
- Added a new sample file: `examples.md`. - Expanded skill documentation with additional usage patterns, quick start instructions, and integration tips. - Updated API usage examples to cover file uploads, status checks, semantic and hybrid search, and metadata filtering. - Clarified multi-tenant isolation and API key scoping behavior. - Improved guidance on project setup, troubleshooting, and database connector configuration.
v1.0.0
Initial release of the Memic SDK integration skill. - Provides step-by-step guidance for integrating Memic's unified search API using the Python SDK. - Helps developers clarify their use case (AI context tool, deterministic search, data source type). - Explains project and data setup through the Memic dashboard and SDK. - Offers example code for setup, document upload, and both semantic and Text2SQL search. - Details best practices for multi-tenant architectures (project mapping). - Includes troubleshooting, data verification steps, and tailored next actions based on actual setup.
Metadata
Slug memic
Version 1.0.4
License
All-time Installs 1
Active Installs 1
Total Versions 5
Frequently Asked Questions

What is memic?

Context engineering platform for AI agents. Upload documents, search with semantic + structured queries, and inject relevant context into LLM prompts. Suppor... It is an AI Agent Skill for Claude Code / OpenClaw, with 365 downloads so far.

How do I install memic?

Run "/install memic" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is memic free?

Yes, memic is completely free (open-source). You can download, install and use it at no cost.

Which platforms does memic support?

memic is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created memic?

It is built and maintained by Punith (@punithg); the current version is v1.0.4.

💬 Comments