Zot: A Lightweight Terminal Coding Agent Now Supports Claude Opus 4.8

Zot is a minimal terminal coding agent distributed as a single static Go binary — no runtime, no Docker, no plugin system with a dedicated package manager. Just the agent loop. Drop it on your $PATH and go. It now supports Claude Opus 4.8 (listed under Anthropic provider) alongside dozens of other models.
Provider Catalog
Zot ships a broad provider catalog with unified IDs across interactive /login, /model, --provider, and --list-models. Subscription-capable providers include Anthropic (Claude Pro/Max), OpenAI Codex / ChatGPT Plus/Pro, Kimi Code, and GitHub Copilot. Direct API providers include Anthropic, OpenAI (Chat Completions & Responses), DeepSeek, Google Gemini, Kimi/Moonshot, Groq, Cerebras, xAI, Together AI, Hugging Face Router, OpenRouter, Mistral, Z.AI, Xiaomi, MiniMax, Fireworks, Vercel AI Gateway, and OpenCode. Cloud/platform providers: Amazon Bedrock, Google Vertex AI, Azure OpenAI, Cloudflare Workers AI, and Cloudflare AI Gateway. Local/compatible providers: Ollama and any OpenAI-compatible endpoint via --base-url.
Four Run Modes
- Interactive — full TUI with streaming output, slash commands, queued messages, and inline side-chat.
- Print —
zot -p <prompt>for one-shot assistant text to stdout. Great for shell pipelines. - Json —
zot --json <prompt>emits NDJSON events to stdout. Perfect for scripts and CI. - RPC —
zot rpcruns as a long-lived child process with NDJSON commands on stdin and events on stdout. Drop into apps written in any language.
Built-in Tools
read— read text files, render PNG/JPG/GIF/WebP inline on modern terminals.write— create or overwrite files, making parent directories as needed.edit— one or more exact-match replacements in an existing file.bash— run a shell command with merged stdout/stderr and a timeout. Use/jailto confine every tool to the current directory. Bash refusessudo,rm -rf /, and other escape patterns as a guardrail.
Extensions
Extensions can be written in any language via subprocess plus JSON-RPC protocol. They register slash commands, expose new tools, intercept tool calls for permission gates, and open interactive panels in the TUI. Install with zot ext install ./my-extension, list with zot ext list, tail logs with zot ext logs my-extension -f. Updates also fast-forward git-installed extensions.
Model Discovery
--list-models and /model show merged catalogs across all providers, including built-in entries and live IDs discovered from GET /v1/models using stored API keys (cached in $ZOT_HOME/models-cache.json for six hours). Custom models can be added via $ZOT_HOME/models.json, with user entries taking precedence.
📖 Read the full source: HN AI Agents
👀 See Also

Anthropic Open-Sources Claude for Legal: Plugin Suite for Contract Review, NDA Triage, and More
Anthropic released Claude for Legal, a repo of plugins, agents, and MCP connectors for legal workflows including vendor agreement review, NDA triage, and regulatory monitoring.

Security scanning skill for AI coding agents automatically checks deployments
A developer created a skill file that enables AI coding agents to automatically scan their own deployments for security issues like exposed secrets, open ports, missing security headers, and leaked source code. The scan runs after every deploy and takes about 30 seconds.

Self-Hosted Contextual Bandit in Rust: Syntra & Lycan for Adaptive Decision Systems
Two open-source projects: Lycan (graph execution language with strategy nodes and learned weights) and Syntra (Docker/API appliance serving compiled Lycan capsules). Found data pipeline bugs before runtime bugs when dogfooding on an AI stock-debate product.

MemAware Benchmark Tests AI Memory Beyond Keyword Search
MemAware is a benchmark with 900 questions across 3 difficulty levels that tests whether AI assistants with memory can surface relevant context when queries don't hint at it. Results show BM25 search scored 2.8% vs 0.8% with no memory, while vector search drops to 0.7% on cross-domain connections.