AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Multi-Agent/
agentweave
agentweave logo

agentweave

Active·★ 42·Apache-2.0·Updated 2026-09-28

AgentWeave provides pre-inference tool routing and a policy-aware function-calling and execution boundary for large language models and multi-agent systems. It significantly reduces the number of tools an LLM needs to consider before making a function call, leading to improved efficiency and reduced token usage.

#LLM Tool Routing#Multi-Agent Orchestration#Function Calling#Policy-Aware Execution#Workflow Automation#Agent Framework Integration
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
#Tool Catalog Management
$ Install
$ python -m pip install agentweave-router
↗ Visit site★ GitHub
01

Features

01Pre-inference tool routing: Reduces the set of tools the model has to reason over before inference.
02Policy-aware execution boundary: Enforces deterministic scope, schema validation, and authorization after tool selection.
03Provider-neutral integration: Works with MCP, LangGraph, AutoGen, A2A, and custom tool catalogs.
04Improved efficiency: Achieves 70.18% fewer tools exposed and 61.70% fewer input tokens compared to baselines.
05Robust runtime controls: Includes argument validation, replay/idempotency guard, and secure HTTP transport.
02

Compatibility

Python
Runtime
Verified via docs
MCP (Multi-Capability Protocol)
Framework
Verified via docs
LangGraph
Framework
Verified via docs
AutoGen
Framework
Verified via docs
A2A
Framework
Verified via docs
Docker
Deployment
Verified via docs
03

Quick start

1
$ python -m pip install agentweave-router
04

Use cases

↳Managing large heterogeneous tool catalogs for LLMs or agents.
↳Enterprise capability catalogs where role, tenant, and policy constraints are paramount.
↳Multi-agent specialist pools and A2A ecosystems requiring efficient tool selection.
↳Integrating with existing agent frameworks like LangGraph and AutoGen for enhanced tool management.
↳Cloud agents and edge runtimes where precise control over tool access and execution is needed.
05

Alternatives

⚡Top VS:
VScli-agent-orchestrator★1.5k→VShive★11.1k→VSAgentflow★27→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
VS
AgentHydra
★44
→
cli-agent-orchestrator logo
cli-agent-orchestrator★ 1.5k
Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions
VSCompare→
hive logo
hive★ 11.1k
Outcome driven agent development framework that evolves
VSCompare→
Agentflow logo
Agentflow★ 27
Production-grade framework for building multi-agent AI systems. Graph-based orchestration, LLM-agnostic (OpenAI, Google GenAI, Anthropic), 3-layer memory (Redis cache + Postgres + vector store), live agents, parallel tool execution, and native MCP. Ships a full ecosystem: backend, REST API + CLI, TypeScript SDK, and React playground
VSCompare→
AgentHydra logo
AgentHydra★ 44
Every local AI coding session in one tab: Claude Code, Codex and OpenCode in a single list, with a queue you can schedule and isolated Claude Desktop instances kept apart. Local, private, MCP-native.
VSCompare→
entwurf logo
entwurf★ 29
Garden-citizen dispatch for pi, Claude Code, Copilot CLI, OMP, Antigravity, and Codex; visible tmux sibling seats for Pi/Claude/Copilot/OMP/Codex, preserving each harness's auth, tools, and transcript; plus Claude/Cortex ACP.
VSCompare→
agent-manager logo
agent-manager★ 615
The fastest workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from one tmux TUI.
VSCompare→
javis-os logo
javis-os★ 279
No description provided.
VSCompare→
openquok-monorepo logo
openquok-monorepo★ 96
Social scheduler: post, schedule, and track everywhere you publish. One workspace with calendar and kanban. Agents run on autopilot via CLI, MCP, and public API—you approve what goes live. Cloud or self-host.
VSCompare→
See all alternatives →
sauravsingla /
agentweave
↗

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.

42Apache-2.0
Last commit3w ago
StatusActive
CategoryMulti-Agent
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit