AgentIndex icon
AgentIndex
claude-delegator logo
claude-delegator
★ 177
vs
agent-lsp logo
agent-lsp
★ 163

claude-delegator vs agent-lsp

claude-delegator: Claude Delegator is a plugin for Claude Code that enables external model second opinions, multi-provider advisory review, and arbiter-mediated consensus across GPT (Codex), Gemini, Grok, and Claude. It includes seven expert roles (Architect, Plan Reviewer, ect.) that can run in advisory or implementation mode, single-shot or multi-turn.; agent-lsp: agent-lsp is a stateful runtime over real language servers. It indexes your workspace once, keeps the index warm, and adds a skill layer that encodes correct multi-step operations. It provides speculative execution, phase enforcement, and token savings for AI agents.

01

TL;DR

claude-delegator logo
claude-delegatorDev Tooling · ★ 177

Architecture decisions and tradeoff analysis

Read claude-delegator full review →
agent-lsp logo
agent-lspDev Tooling · ★ 163

Multi-project sessions: work across projects without reconfiguring

Read agent-lsp full review →
02

Side-by-Side Comparison

Field
claude-delegator logoclaude-delegator
agent-lsp logoagent-lsp
Category
Dev Tooling
Dev Tooling
Stars
★ 177
★ 163
License
MIT
MIT
Install Command
/plugin marketplace add antonbabenko/agent-plugins && /plugin install claude-delegator@antonbabenko && /claude-delegator:setup
curl -fsSL https://raw.githubusercontent.com/blackwell-systems/agent-lsp/main/install.sh | sh
Updated
1w ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
ai-agents, ai-coding, claude
agentskills, ai-agents, ai-tooling
03

Features

claude-delegator logoclaude-delegator
017 domain experts for different problem types
02Support for GPT, Gemini, and Grok providers
03Dual mode: advisory (read-only) and implementation (write)
04Auto-routing: Claude detects when to delegate from your request
05Synthesized responses: Claude interprets expert output, never raw passthrough
agent-lsp logoagent-lsp
0165 tools for code intelligence
0230 CI-verified languages
0324 multi-step agent workflows (skills)
04Speculative execution to simulate changes before applying
05Phase enforcement to block out-of-order tool calls
04

Use Cases

claude-delegator logoclaude-delegator
↳Architecture decisions and tradeoff analysis
↳Stuck debugging after multiple failed attempts
↳Security review and vulnerability assessment
agent-lsp logoagent-lsp
↳Multi-project sessions: work across projects without reconfiguring
↳Polyglot development: handle Go, TypeScript, Python in one session
↳Large monorepos: one server handles all languages
FAQ

FAQ

What is the difference between claude-delegator and agent-lsp?
Both claude-delegator and agent-lsp are in the Dev Tooling category. claude-delegator has 177 stars, while agent-lsp has 163 stars.
Which is better, claude-delegator or agent-lsp?
The best choice depends on your use case. Choose claude-delegator if Architecture decisions and tradeoff analysis, and agent-lsp if Multi-project sessions: work across projects without reconfiguring.
Is claude-delegator free or open source?
Yes, claude-delegator is open source on GitHub (MIT).
Is agent-lsp free or open source?
Yes, agent-lsp is open source on GitHub (MIT).
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
→

Related

Alternatives to claude-delegator →Alternatives to agent-lsp →claude-delegator details →agent-lsp details →