Supercharge AI Agents, Safely

tool-routing 开源项目推荐(80 个)
tool-routing 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 80 个仓库Deterministic, fail-open tool routing for Hermes Agent with an optional local-model fallback.
Semantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev
n2-QLN: Intelligent Tool Router & Semantic Search Layer for MCP. Connect 1,000+ tools through 1 interface. Prevent AI model confusion and maximize context window efficiency
Pre-inference tool and agent routing for MCP, A2A and tool-rich LLM systems. Reduce candidate tools before model inference with policy-aware routing and recovery.
local-first MCP discovery runtime for agents — search before invoke, reduce prompt bloat, and route to local MCP tools
Opencode-Raven keeps noisy tool work behind a focused Raven agent, so your main model gets compact answers instead of raw search results, docs pages, GitHub examples, MCP output, or large MCP schemas.
AI Workload Control Layer for routing deterministic, reusable, retrieval-needed, tool-needed, and provider-needed work before model invocation.
MetaMCP keeps core MCPs direct and routes the long tail through 3 lazy tools and reviewed declarative Methods.
A 1.5B model shown all 80 tools picks the right one half the time — not because it can't call tools, but because it can't find them. Tier adapts the tool presentation to model size: +10pp accuracy and 97% fewer tool tokens on sub-4B models.
Search 1,000 MCP tools through two interfaces in DeepSeek Harness. Load exact schemas on demand and keep structured results usable across tool calls.
Jev-powered MCP tool routing for Codex
Budget-aware context compilation and context firewall for tool-heavy AI agents.
Semantic routing for MCP tools - .NET library that indexes MCP tool definitions and returns the most relevant tools via vector search
Decision-first, OpenAI-compatible AI router powered by Jev typed decisions. Routes every request to the right LLM, agent or tool with explainable traces, fallbacks, guardrails and cost savings.
An MCP server for discovering, ranking, and retrieving agent skills while minimizing context usage.
A governed skill system for long-horizon human-AI collaboration.
Let a decision model pick your agent's MCP tools, not the LLM. An MCP gateway routed by Jev: 649 tools, 1/32 the cost of LLM routing.
Intelligent tool routing extension for pi coding agent - automatically selects the best tool stack for each task
Orchestration MCP Server - Routes tool calls to MCP backends
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/tool-routing。
- 该话题在 GitHub 上共有 80 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 937 Star,覆盖 5 种主要语言,数据更新于 2026-11-11。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。