nexo-rs

Bounded auto-iteration for a prompt with explicit stop predicates.

Memory hygiene workflow to classify, deduplicate, and promote durable knowledge across local memory layers.

Bounded simplification pass for a file or hunk that preserves behavior while reducing complexity.

Turn a repeatable workflow into a reusable local SKILL.md with explicit steps, criteria, and safe defaults.

Bounded auto-debug loop for failing build/test commands with evidence-first diagnosis.

Safely update Nexo config files with read-before-write merges, schema-aware mapping, and reload/restart awareness.

Bounded acceptance verification that runs concrete checks and an explicit LLM judge over evidence.

Web search via Brave Search API with clean JSON results and minimal SEO noise.

Inspect and control local Docker containers.

HTTP probe (status + latency) and TLS certificate inspection (expiry, issuer, SANs).

Authenticate against the user's own Google account (Gmail, Drive, Calendar, Sheets, etc.) via the installed-application OAuth 2.0 flow and make authenticated HTTP calls.

Gmail, Calendar, Tasks, Drive, Contacts (People), and Photos via Google APIs with OAuth refresh tokens.

Extract plain UTF-8 text from local PDF files; pipeline input for summarize.

Control VMs/containers in Proxmox VE via REST API.

Capture JPG frames or short MP4 clips from RTSP/HTTP IP cameras via ffmpeg.

Inspect this agent's stored JSONL session transcripts — list, read, search, or recall recent turns.

Control Spotify playback via Web API — now playing, search, play/pause/next/previous.

Computational queries — math, science, conversions, and verified facts.

Read 1Password secrets via the `op` CLI with a service-account token. Secret values are metadata-only by default.

Drive a managed Chrome session via CDP. Navigate, click, fill forms, read the DOM, take screenshots, run JS.

Manage Cloudflare zones, DNS records, and cache via API token.

Resolve DNS records (A, AAAA, MX, TXT, CNAME, NS, SOA, SRV, CAA), PTR reverse, and WHOIS.

HTTP GET/POST utility with size cap, SSRF guard, retries, and circuit breaker.

Read pull requests, issues and CI checks via GitHub REST API.

Rich POI lookup via Google Places API (requires paid API key).

Synthesize text to speech using Microsoft Edge Read Aloud voices (no API key).

Transcribe audio files (≤25 MB) to text via OpenAI-compatible Whisper API.

Forward and reverse geocoding via Nominatim (no API key, ~1 req/sec).

Fetch and parse RSS, Atom, and JSON feeds.

Run shell commands on remote hosts via SSH, and transfer files via SCP. Allowlist-gated.

Summarize text or local UTF-8 files via OpenAI-compatible chat completions.

Durable multi-step flows that survive process restart, coordinate waits, and expose revision-safe state.

Extract text from images and scanned PDFs via the local Tesseract binary.

Run long-lived commands in detached tmux sessions; send keys; scrape pane output.

Translate text between languages via LibreTranslate or DeepL.

Extract frames or the audio track from a local video file via ffmpeg. Pairs with openai-whisper for audio→text.

Current conditions and 1–16 day forecasts via Open-Meteo (no API key).

Search Wikipedia and fetch article summaries or extracts.

Download videos, extract audio, or fetch metadata from YouTube, Twitter/X, Instagram, TikTok, and many more sites.