Search

AI model: sagnikM/hill-tooluse-qwen25-7b-priorlr1e-5-postlr1e-6-kl3e-3-1024x1024-seed42-step250-prior

AI model: sagnikM/hill-tooluse-qwen25-3b-priorlr1e-5-postlr1e-6-kl3e-4-1024x1024-seed42-step250-prior

A next-generation AI coding agent built for serious developers — blazing-fast terminal UI, multi-model AI orchestration, autonomous coding, swarm coordination, 40+ tools, and advanced agentic workflows.

中文问数（ChatBI）智能体：语义层 + SQL 智能体双路径，sqlglot 安全门，浏览器内 Python/DuckDB（WebAssembly）+ Cloudflare Workers AI

Universal typed reranking for RAG, search, agents and arbitrary Python objects.

Pick the right LLM for every task: filter by context, output and cost limits, then let Jev choose the most efficient model.

Upload local AI agent sessions to turns.dev

The Husk tool-calling loop and its built-in tools.

Javascript library to display flowise chatbot on your website

Perception-aware evidence-first engineering runtime with adaptive context, capability routing, visual/browser verification, weak-model recovery and benchmark-gated execution for OpenCode

React library to display flowise chatbot on your website

Share a local folder for smooth real-time collaborative editing with your coding agent.

Multi-agent development orchestrator — autonomous task planning, execution, and validation with Claude Code integration

Integration bridge between AI agent frameworks and stellar-agent-guard smart accounts: pre-flight policy interception, agent-auth transaction signing, cost pre-checks, and on-chain event telemetry. Full recipient/amount enforcement — spend caps, allowlist

Agentic terminal coding assistant: multi-provider LLM loop with local file/shell/web tools in an Ink (React) TUI.

Per-turn skill routing for LangChain deepagents: a pluggable judge (Jev included, or your own) loads only the SKILL.md skills each turn needs, keeping a catalog of hundreds out of the prompt.

Thin async client for the HostAnAgent public protocol

Local-first Agent Work Intelligence for coding agents: usage truth, recorded work, and honest joins

Space Bunny Alpha is an anonymous large model with blazing-fast inference, strong coding capabilities and native multimodal input support. It delivers adjustable reasoning effort, and a 1M-token context window. Space...

Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...