AgentRunDB

AgentRunDB

Know what actually works.

AgentRunDB tests AI agents, models, skills and MCP servers — and publishes reproducible compatibility data, real runs and working recipes.

Explore CompatibilityView Runs

Recently Verified

Claude Code × DeepSeekPartial Support

5 runs · Success rate 80% · Last verified 2026-08-18

OpenCode × DeepSeekPartial Support

2 runs · Success rate 50% · Last verified 2026-08-18

Codex CLI × DeepSeekPartial Support

2 runs · Success rate 50% · Last verified 2026-08-18

Explore AgentRunDB

Structured compatibility data, backed by real runs.

Compatibility

Does agent A actually work with model or tool B? Tested combinations with exact versions and evidence.

Runs

The underlying facts: every test run with environment, duration, cost and known issues.

Recipes

Reproducible configurations backed by AgentRunDB runs — not AI-generated tutorials.

Tested Recipes

Reproducible configurations backed by real runs.

Develop a Custom Plugin for DeepSeek Harness (dsh)

Step-by-step guide to writing and publishing a modular Cordis-based plugin for DeepSeek Harness.

● Backed by 0 AgentRunDB runs

Attach GitHub MCP Server to Codex CLI

Give OpenAI Codex CLI direct repository inspection, PR creation, and issue tracking capabilities via Model Context Protocol.

● Backed by 2 AgentRunDB runs

Connect OpenCode to DeepSeek V3

Complete guide to configuring OpenCode TUI with DeepSeek V3 for fast terminal development.

● Backed by 2 AgentRunDB runs

AgentRunDB Stats

9

Verified Runs

15

Compatibility Records

8

Agents

8

Skills & MCP Servers