Exgentic
exgentic.ai
- Linux
- Web
- API
- Self-hosted
6.6 Club score Visit exgentic.ai
What the maker publishes
- Agents
- Listed agents include LiteLLM Tool Calling, SmolAgents, OpenAI MCP, Claude Code, Codex CLI, and Gemini CLI. source
- Available agents
- The listed agents include LiteLLM Tool Calling, HuggingFace SmolAgents, OpenAI MCP, Claude Code, Codex CLI, and Gemini CLI. source
- Available benchmarks
- The framework lists tau2, appworld, browsecompplus, swebench, hotpotqa, gsm8k, and bfcl benchmarks. source
- Benchmark handling
- Exgentic says it does not modify benchmarks or agent implementations, though it may adapt interfaces to its unified protocol. source
- Benchmarks
- Listed benchmarks include τ²-bench, AppWorld, BrowseComp+, SWE-Bench, HotpotQA, GSM8K, and Berkeley Function Calling Leaderboard. source
- Benchmarks
- The leaderboard covers personal assistance, customer service, technical support, deep research, and software engineering benchmarks. source
- Evaluation approach
- Exgentic says it avoids prompt optimization and reports results on 100 sampled tasks per benchmark. source
- Evaluation domains
- The leaderboard covers personal assistance, customer service, technical support, deep research, and software engineering tasks. source
- Evaluation framework
- Its framework provides a consistent interface for evaluating agents on benchmarks to compare performance and reproduce results. source
- Framework
- Exgentic provides a consistent interface for testing agents across benchmarks and domains to compare performance and reproduce results. source
- Installation
- The project documents installation as a command line tool with uv and use as a Python library with uv or pip. source
- Integrations
- The README documents API credentials for OpenAI and Anthropic models and support for Hugging Face models and Jobs. source
- Isolation
- The repository documents a Docker runner for full container isolation, requiring Docker to be installed and running. source
- License
- The framework is distributed under the Apache License 2.0. source
- License and support
- The repository states that Exgentic is licensed under Apache License 2.0 and directs support questions to GitHub issues. source
- Local use
- The README documents installation as a command-line tool or Python library and includes an evaluation dashboard command. source
- Methodology
- Exgentic says it avoids prompt optimization and reports results on 100 sampled tasks per benchmark. source
- Model integrations
- The quick start documents OpenAI and Anthropic API credentials, and the repository also describes support for Hugging Face models or evaluations on Hugging Face Jobs. source
- Open results
- The evaluation pipeline, agent implementations, configuration, and results are available for reproducing evaluations. source
- Product
- Exgentic is an open agent leaderboard that compares general purpose AI agents across diverse benchmarks. source
- Purpose
- Exgentic is an open agent leaderboard that evaluates general purpose AI agents across diverse domains. source
- Reproducibility
- The evaluation pipeline, agent implementations, and configuration are available in the repository; the project notes results may vary with model versions or nondeterministic outputs. source
- Run limits
- Evaluation sessions default to limits of 100 steps and 100 actions, and stop when either limit is reached. source
- Security and isolation
- The README documents a Docker runner for full container isolation when running evaluations. source
Checked against the maker's pages on 9 Oct 2026.