harness-starter-kit
AI codingPrompt-first starter kit for turning repeated coding-agent instructions into durable repo rules, knowledge stores, feedback loops, and drift checks.
2,743 results · Page 19 of 77
Prompt-first starter kit for turning repeated coding-agent instructions into durable repo rules, knowledge stores, feedback loops, and drift checks.
A canvas-based IDE that can help you handle the tedious and confusing parts of coding.
Transparent MCP proxy that intercepts JSON-RPC messages, measures latency, stores traces in SQLite, PostgreSQL or MySQL, and exports OpenTelemetry spans.
Hermes IDE is a vendor-neutral desktop console for coding agents, terminal-first. It lets Claude Code, Codex, Antigravity, OpenCode, GitHub Copilot, goose, Aider, Kiro, or user-defined commands each run in a separate terminal, with each task having its own branch, and prompts through a unified inbox which agents are waiting for the user. It supports macOS, Linux, and best-effort Windows, is free, and is source-available under the BSL 1.1 license. This product is not affiliated with Nous Research or its Hermes Agent.
Bilingual (English/Spanish) dual-memory system on PostgreSQL, pgvector and NVIDIA NIM with progressive retrieval, deduplication, checkpoints and auto-repair.
No-code hiring software with AI screening and automated follow-ups.
Hash-anchored file edits: read files with line anchors, validate anchors against current content and reject stale writes.
Read-only debugging for Hono apps: recent exceptions with their requests, logs and queries, requests filtered by status or duration, and the slowest queries.
No-code AI platform for building websites, apps, and business solutions.
No-code platform to build, deploy, and manage AI-powered Assistants for exceptional customer experiences.
AI-powered tool for translating JSON files and Markdown blogs.
AI-powered i18next translation tool for automatic app localization into 80+ languages.
No-code platform for creating interactive, immersive web content with Generative AI.
🎖️ 📇 🏠 - Retrieval over your own data with Infino (BM25 full-text, vector, hybrid and SQL), an embedded engine on Apache Parquet over object storage.
Interact with iOS simulators: get simulator information, control UI interactions and inspect UI elements.
Performance testing with JMeter.
Self-hostable GPU-aware job broker: dispatch long-running or GPU jobs that outlive the session, route them by VRAM tier and monitor them across sessions.
Through the integrated model of "visual operations + low-code logic orchestration + AI assistance", it lowers the development threshold and improves development efficiency, while also balancing development flexibility and system stability, providing developers and enterprises with full-process development support from "rapid prototype building" to "full-featured system implementation".
🎖️ 🦀 🏠 🍎 🪟 🐧 - Duplicate code detection with jscpd: check snippets and files for copy/paste duplication against a scanned project before committing.
AI extensions for Jupyter notebooks with natural language code generation.
Justfile integration: run CLI or script commands with parameters and environment variable support.
AI-first headless CMS for solopreneurs and indie developers, focusing on simplicity and speed.
JVM-based MCP server implementation.
Kailua Labs: Low-code platform for building AI-powered Multisearch applications.
Scans deployed HTML and JavaScript for exposed secrets while recognizing public browser credentials that should not be treated as leaks.
Kimi CLI
Platform for AI developers to create APIs and app developers to integrate AI.
Local code graph for coding agents: find code by intent, follow callers and references, inspect blast radius and trace dependencies across repositories.
Kodwai calls itself the "LeetCode of the AI era" and is a coding assessment platform for the age of AI agents. It argues that traditional LeetCode-style algorithm problems can no longer prove a developer's ability, because agents can solve these problems in seconds, and grinding problems only demonstrates memorization ability. Kodwai attempts instead to assess a new way of working: having developers point agents at real problems, identify and correct agents when they "confidently make mistakes," and check the results they actually deliver. According to its description, this ability is what determines a developer's level, and it is what Kodwai scores, under conditions involving real problems and using your own agent. At present, the materials do not provide details such as the specific problem format, scoring mechanism, which agents are supported, whether it is paid, the platform entry point, or usage steps.
Accessible KoliBri web component samples, specs, docs and scenarios.
AI-powered analytics platform for business insights and data-driven decisions.
Interactive platform for hands-on coding and tech learning with labs and AI assistance.
Query Langfuse traces, debug exceptions, analyze sessions and manage prompts for LLM applications.
Query Langfuse traces and observations, debug exceptions, analyze sessions, scores and datasets, and manage prompts.
LAYSO AI provides one OpenAI-compatible API key to access 300+ AI models across text, coding, image, video, and audio.
A programming learning platform for algorithm engineers.