ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

Langflow

Langflow is a powerful tool for building and deploying AI-powered agents and workflows. llm-flow, python, agents, chatgpt, generative-ai.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/bytesagain/llm-flow
Or

LLM Flow

An AI toolkit for configuring, benchmarking, comparing, prompting, evaluating, fine-tuning, analyzing, and optimizing LLM workflows. Each command logs timestamped entries to local files with full export, search, and statistics support.

Commands

Core AI Operations

CommandDescription
llm-flow configure <input>Record a configuration change (or view recent configs with no args)
llm-flow benchmark <input>Log a benchmark run and its results
llm-flow compare <input>Record a model or output comparison
llm-flow prompt <input>Log a prompt template or prompt engineering note
llm-flow evaluate <input>Record an evaluation result or metric
llm-flow fine-tune <input>Log a fine-tuning session or parameters
llm-flow analyze <input>Record an analysis observation
llm-flow cost <input>Log cost tracking data (tokens, dollars, etc.)
llm-flow usage <input>Record API usage metrics
llm-flow optimize <input>Log an optimization attempt and outcome
llm-flow test <input>Record a test case or test result
llm-flow report <input>Log a report entry or summary

Utility Commands

CommandDescription
llm-flow statsShow summary statistics across all log files
llm-flow export <fmt>Export all data in json, csv, or txt format
llm-flow search <term>Search all entries for a keyword (case-insensitive)
llm-flow recentShow the 20 most recent activity log entries
llm-flow statusHealth check: version, entry count, disk usage, last activity
llm-flow helpDisplay full command reference
llm-flow versionPrint current version (v2.0.0)

How It Works

Every core command accepts free-text input. When called with arguments, LLM Flow:

  1. Timestamps the entry (YYYY-MM-DD HH:MM)
  2. Appends it to the command-specific log file (e.g. benchmark.log, cost.log)
  3. Records the action in a central history.log
  4. Reports the saved entry and running total

When called with no arguments, each command displays the 20 most recent entries from its log file.

Data Storage

All data is stored locally in plain-text log files:

~/.local/share/llm-flow/
├── configure.log     # Configuration changes
├── benchmark.log     # Benchmark results
├── compare.log       # Model comparisons
├── prompt.log        # Prompt templates & notes
├── evaluate.log      # Evaluation metrics
├── fine-tune.log     # Fine-tuning sessions
├── analyze.log       # Analysis observations
├── cost.log          # Cost tracking
├── usage.log         # API usage metrics
├── optimize.log      # Optimization attempts
├── test.log          # Test cases & results
├── report.log        # Report entries
├── history.log       # Central activity log
└── export.{json,csv,txt}  # Exported snapshots

Each log uses pipe-delimited format: timestamp|value.

Requirements

Metadata

Stars3500
Views0
Updated2026-03-27
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-bytesagain-llm-flow": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.