Search

Check whether your agent instruction files reach the agent at all: Codex, Claude Code, Cursor, Copilot.

Local developer MCP server with Streamable HTTP, OAuth 2.1, filesystem tools, commands and Git repository context.

22-agent Mixture-of-Agents pipeline with LongLoop for 24h autonomous iteration: smart routing sends easy tasks to Flash, hard tasks to flagships, cutting token costs ~90%. One-command deploy（一键部署，22 个 agent 的 MoA 流水线，长程循环可自主迭代 24 小时，智能路由省约 90% token 成本）

A local-first agentic coding harness: streaming tool loop, permission gating, context compaction, subagents, and any LLM provider.

Task-driven context compression for LLM agents with analytical compression strategy

Stream Codex, Claude, Kimi Code, and OpenCode worker progress to an explicit Telegram destination

Self-observing AI agent SDK: OpenTelemetry instrumentation for AI SDK agents plus an LLM-over-traces behavioral drift detector. Bring your own model client — no provider SDKs bundled.

Ollama Cloud web search and fetch plugin for Hermes Agent

Perseus Vault persistent, local, encrypted memory for Pydantic AI agents — exposed as a Toolset.

This model always redirects to the latest model in the DeepSeek V4 Flash family.

Project-neutral autonomous multi-agent supervision control plane

🔌 Portable uncensored AI agent that runs from USB/SSD. 13 autonomous tools (deep search, OSINT, code execution), persistent memory, 5 GGUF models, zero install, zero traces. Cross-platform (Windows + Linux).

AI Agent platform for incident triage & project Q&A on OpenHands — Git sync, logs, config center, Ingress/Webhook

Lighthouse for your coding agent — scans local Claude Code session history for recurring failures.

Offline-first agentic AI framework with planning, tool orchestration, memory, and local LLM support built using FastAPI and Ollama.

完整的 Godot 4.6 卡牌 RPG：包含回合制卡牌战斗、牌组与状态系统、仪式锻造、城市探索、NPC/委托/情报和小游戏、高塔生成与推进、可离线降级的 AI GM 叙事、运行时美术与 7 首 BGM；另含可独立测试的 TypeScript/WebSocket 权威服务端原型、Godot/Vitest/WebQA 测试和跨平台导出配置。

A lightweight coding agent CLI built with smolagents

OpenCAD AI agent — natural-language modelling on top of the OpenCAD core

Agent memory gated on surprise, budgeted on attention, with provenance and validity intervals.

Open host agent for the FlashML fragmented-compute network: join, benchmark, execute sandboxed ML tasks, earn contribution credits.