Waggle
Waggle shows which files an AI agent actually opened before it answered. Instead of pasting whole documents between agents, it hands over short references that can be traced back to the source, so you can check whether an answer was grounded in what you gave the agent and send it back when it skipped the reading. It plugs into agent harnesses over MCP.
Updated
✨ Try AgentScout's free AI image generator →Good for: building AI agents, working with documents, connecting tools with MCP, evaluating agents
Use cases
About Waggle
Waggle is listed in our evals & observability category and is aimed at builders. Waggle shows which files an AI agent actually opened before it answered. Instead of pasting whole documents between agents, it hands over short references that can be traced back to the source, so you can check whether an answer was grounded in what you gave the agent and send it back when it skipped the reading. It plugs into agent harnesses over MCP. Pricing, as the maker states it: Open source. Maturity: Active. We last checked the official link on 2026-10-24.
Waggle at a glance
- Category: Evals & observability
- Built for: Developers and teams building with AI agents
- Pricing: Open source (as the maker states it)
- GitHub: modiqo/waggle · 635 stars (as of Oct 24, 2026)
- Official site: waggle.sh
- Listed on AgentScout: Oct 24, 2026
Waggle FAQ
What is Waggle?
Waggle shows which files an AI agent actually opened before it answered. Instead of pasting whole documents between agents, it hands over short references that can be traced back to the source, so you can check whether an answer was grounded in what you gave the agent and send it back when it skipped the reading. It plugs into agent harnesses over MCP.
How much does Waggle cost?
Waggle's pricing, as the maker states it: Open source. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Where can I find Waggle's source code?
On GitHub at modiqo/waggle, which had 635 stars as of Oct 24, 2026.
What are alternatives to Waggle?
Similar tools include Userpilot Agent Analytics, Firedrill, SWE-bench, Agent Memory Leaderboard, AgentEnv Framework and Braintrust.
Facts from our link-checked listing, the GitHub repository and the official site. See something wrong? Suggest an edit.
Waggle ratings and reviews
Be the first to rate Waggle: tap 1 to 5 stars below. A written review is optional.
Waggle alternatives
Other evals & observability tools in our directory. See all evals & observability tools →
Userpilot Agent Analytics
Userpilot Agent Analytics shows product teams how users actually get on with the AI agent inside their app. It reads the agent's conversations at scale and reports whether people got what they needed or left frustrated, so teams can see where the agent fails, which requests it can't handle and how agent use ties back to product engagement, alongside Userpilot's existing product analytics.
Firedrill
A simulation platform for testing AI agents before launch: it runs your agent through realistic scenarios with simulated users and tools, scores results against checks or rubrics and shows where it fails. Includes a remote MCP server.
SWE-bench
Benchmark that tests whether language models and coding agents can resolve real GitHub issues, with multimodal and verified variants.
Agent Memory Leaderboard
Public leaderboard and open evaluation protocol, run by a group of universities and labs, for comparing long-term memory systems for agents in recurring submission rounds.
AgentEnv Framework
AgentEnv Framework is Scale AI's open-source Python SDK and CLI for building RL environments for agents: containerized worlds with realistic apps and data behind an MCP gateway, plus tasks (as DAGs) that grade any agent in any sandbox.
Braintrust
Evals and observability platform for AI products.
Popular searches with this tool
🏆 See also: Best AI Agent Observability & Eval Tools · All best-of lists
🧭 Task guides: RAG and document tools for building AI agents
Badge for makers
Built Waggle? Add this badge to your README or site. It links back to this page. About badges
