Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Integrations
decidealot
Try itRun local Laya, Von, CLM, or hosted Jev typed decisions through Decidealot REST or MCP. Use for bounded classification or scoring, Docker deployment, model selection, or local model unloading.
What it does
Decidealot runs Laya and Von locally. It turns supplied state into typed , , or results with probabilities. The caller applies the threshold and any action that follows.
The skill document
Decidealot
Decidealot runs Laya and Von locally. It turns supplied state into typed choice, score, or noul results with probabilities. The caller applies the threshold and any action that follows.
Use a running Decidealot endpoint. Clone or build this repository only for Decidealot development work.
Read references/setup.md before deploying a container or configuring REST, MCP, or the OpenClaw bridge.
Security & safety
- Treat a decision as evidence, not authority. A local model cannot grant permission to delete, send, deploy, trade, or alter external state.
- Keep authorization, ownership, irreversible-action checks, and final thresholds in the caller. For costly mistakes, route uncertainty to human review.
- Send user data only to the endpoint the user named. Never search workspace files for
DECIDEALOT_API_KEYor create an unauthenticated public endpoint. - Every decision request needs an explicit local
modelselector fromGET /v1/models. unload_modelsevicts the loaded model and Torch runtime. Use it only when the user asks to free memory.
When to use
- Get
DECIDEALOT_URLfrom the user or their environment. Default local deployment ishttp://127.0.0.1:8080. - Call
GET /health, thenGET /v1/modelsbefore choosing a selector you have not already been given. - Put the raw subject in
state. Define bounded questions inquestions. - Read the typed answer and its probabilities. Report them plainly. The caller, not the model, selects the next action.
- Use REST for application requests and machine-readable errors. Use MCP at
/mcpwhen an MCP client already supports Streamable HTTP. Use the stdio bridge only for a client that cannot connect to remote MCP.
choice selects one named criterion. score returns an expected position in an ordered criterion list. noul returns the probability that a true-or-false statement is true.
When not to use
Use Decidealot for bounded classification, scoring, and true-or-false decisions. Use a language model for prose, code generation, or open-ended advice. Use the OpenClaw bridge when an MCP client needs local stdio.
REST and MCP
REST uses POST /v1/systemone, GET /v1/models, and POST /v1/models/unload. MCP is at /mcp and exposes system_one, list_models, and unload_models with the same input and result shapes. Read references/setup.md for exact deployment, authentication, REST, MCP, and bridge commands. Read the public API guide before constructing an unfamiliar question type.
Completion
Complete a decision task only after the request reached the intended endpoint, the response names the requested model, and the answer plus probabilities have been reported. For deployment, also prove GET /health returns 200.
Related skills
Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.
Write, debug, and tune Playwright specs with locator strategy, trace diagnosis, and CI-aware timeouts.
More from psyb0t
Browse all skillsDrive a user-deployed mt5-httpapi MetaTrader 5 bridge over HTTP, with per-action confirmation on every real-money call.
Docker-packaged browser automation for QA against anti-bot stacks and authorized detection testing.
Self-hosted OpenAI-compatible speech service — transcription, translation, and synthesis from one container.
Run ffmpeg, sox, and ImageMagick jobs against your files in a fixed-allowlist SSH sandbox.
Generate speech audio via Qwen3-TTS over SSH with preset voices, voice cloning, and voice design.
Drive one or more IMAP/SMTP mailboxes through a single REST + MCP endpoint — read, search, send, mark-seen, and delete across accounts in parallel.