blazorly-harness
A token efficient, local LLM friendly agentic coding harness: a complete agent runtime (agent loop, tool pipeline, sandboxing, session persistence) with four front-ends — a Blazor web UI, a headless CLI, and JSON-RPC / ACP stdio servers for editors a
blazorly-harness at a Glance
- Pricing
- Free
- How you use it
- Web UI, headless CLI, desktop app, or JSON-RPC / ACP stdio servers
- Who it's for
- Developers who want an AI coding agent for browser-based work, CLI, editors, or automation
- Works with
- DeepSeek OpenAI Anthropic xAI Ollama LM Studio MCP servers
blazorly-harness Key Features
- Orchestrate sub-agents
- Persist sessions
- Read and edit files
- Run commands
- Search the web
Can't Find What You're Looking For?
We build custom AI agents tailored to your specific business needs. From ideation to deployment, TinyAI.Tools is your partner in AI innovation.
No commitment required. Let's discuss your ideas.
blazorly-harness Alternatives
code-assistant
An LLM-powered, autonomous coding assistant. Also offers an MCP and ACP mode. - stippi/code-assistant
DeepCode
"DeepCode: Open Agentic Coding (Agent Harness & Loop Engineering & Multi-Agent Orchestration)" - HKUDS/DeepCode
Radian
radian is a fast, efficient coding agent in one Rust binary. Every step is journalled, and the headless command prints each step as a JSON line and exits with a code that says how it ended.
coddy-agent
Coddy Agent is a distroless-friendly agent harness: one Go binary with a terminal console, ACP for editors, an embedded web UI, a Telegram gateway, a cron scheduler, a swarm relay and remote control, plus rules, skills, subagents, hooks, MCP and your
command-code
The coding agent that made open models work. Tool call repairs on every model, best in class token efficiency on read and shell tools, 99%+ cache hit rates, and taste-1, which learns your coding taste. 100K+ developers, 40K+ paid customers, 130T+ tok
apexo-code
Apexo: An open-source, general-purpose coding agent for terminal (TUI), web, and desktop with autonomous goals, workflows, persistent memory, command sandboxing, and first-class support for Gemini, Grok, and OpenAI-compatible models. - cluster1900/ap