Search

SOLAI Agent is a local-first AI agent and coder that runs locally on your computer.

本地原型工作台：左侧树形导航 + 中间原型预览 + 右侧 AI Agent（OpenCode）。PRD 与 HTML/JS 原型协作，含自动化检查。

Wave-based experiment scheduler for AI agents: run hundreds of parameterized experiments (benchmarks, sweeps, paper reproduction) with durable job state, metric extraction, and agent-friendly summaries.

AI model: mradermacher/Polypsyche-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto-Logic-i1-GGUF

AI model: TeichAI/Gemma-4-31B-Fable-5-Agent-Distill

开源终端 AI 编程 Agent：以在线 Evidence Runtime 验证链（LLM 输出是 Claim、工具结果才是 Evidence）为核心，SWE-bench_Lite 官方评测 36.7% 实例级通过率（可复现报告）。支持 7 种推理范式、MCP 工具、多模型。Python。

A general AI playground for Don't Starve, combining rule-based logic, goal systems, and LLM-assisted planning.

Lightweight workflow SDK and mtrxai CLI for mtrxai workflow developers.

Native OpenAI-compatible agent harness for LiteyukiBot v7.

CrewAI memory backed by Citadel: encrypted at rest, with deletes that destroy the key

Python client for Recuerdos AI, a self-hostable long-term memory service for AI agents.

Connect OpenAI function calling directly to a remote MCP server

MARLA: Multi-Agent Reinforcement Learning Architecture for NASimEmu

YantrikDB integration for LangChain — cognitive memory as a VectorStore and ChatMessageHistory. Stored memories decay, consolidate, and get contradiction-checked.

Autonomous multi-agent ML research platform

Nightly autonomous code review of local git branches through Claude Code

Building open-core, autonomous AI orchestration tools and C# state-graph extensions natively embedded inside the Unity Editor.

War - agentic warfare simulation

Your personal coding assistant for macOS

Requirements discovery as an Agent role: Scout-driven dialogue turns vague ideas into implementable, verifiable requirements - Anchorlaw's upstream input contract.