Metabuilder-Labs/tokenjam-bench

Add a Troubleshooting section to the README about 11 hours ago

documentation good first issue

11

Comprehensive benchmarking and evaluation framework for TokenJam

Python

#agentic-ai#ai#cli#duckdb#hermes#hermes-agent#llm#ml#openclaw#python

Add a worked Wilson confidence-interval example to the statistics docs about 11 hours ago

documentation good first issue

Metabuilder-Labs/tokenjam-bench

11

Comprehensive benchmarking and evaluation framework for TokenJam

Python

#agentic-ai#ai#cli#duckdb#hermes#hermes-agent#llm#ml#openclaw#python

Document the mock-directive format in the development docs about 11 hours ago

documentation good first issue

Metabuilder-Labs/tokenjam-bench

11

Comprehensive benchmarking and evaluation framework for TokenJam

Python

#agentic-ai#ai#cli#duckdb#hermes#hermes-agent#llm#ml#openclaw#python

Add an end-to-end replay example to the replay docs about 11 hours ago

documentation good first issue

Metabuilder-Labs/tokenjam-bench

11

Comprehensive benchmarking and evaluation framework for TokenJam

Python

#agentic-ai#ai#cli#duckdb#hermes#hermes-agent#llm#ml#openclaw#python

Show confidence intervals on the dashboard 1 day ago

help wanted

Metabuilder-Labs/tokenjam-bench

11

Comprehensive benchmarking and evaluation framework for TokenJam

Python

#agentic-ai#ai#cli#duckdb#hermes#hermes-agent#llm#ml#openclaw#python

Add a built-in llm-as-judge backend 1 day ago

help wanted

Metabuilder-Labs/tokenjam-bench

11

Comprehensive benchmarking and evaluation framework for TokenJam

Python

#agentic-ai#ai#cli#duckdb#hermes#hermes-agent#llm#ml#openclaw#python

Add an `aime` math benchmark suite 1 day ago

help wanted

Metabuilder-Labs/tokenjam-bench

11

Comprehensive benchmarking and evaluation framework for TokenJam

Python

#agentic-ai#ai#cli#duckdb#hermes#hermes-agent#llm#ml#openclaw#python

Implement Google agent / tool-calling support 1 day ago

help wanted

Metabuilder-Labs/tokenjam-bench

11

Comprehensive benchmarking and evaluation framework for TokenJam

Python

#agentic-ai#ai#cli#duckdb#hermes#hermes-agent#llm#ml#openclaw#python

Add Ollama / local-model support (OpenAI-compatible endpoint) 1 day ago

help wanted

Metabuilder-Labs/tokenjam-bench

11

Comprehensive benchmarking and evaluation framework for TokenJam

Python

#agentic-ai#ai#cli#duckdb#hermes#hermes-agent#llm#ml#openclaw#python

Add Cohen's h effect size to the statistics module 1 day ago

good first issue

Metabuilder-Labs/tokenjam-bench

11

Comprehensive benchmarking and evaluation framework for TokenJam

Python

#agentic-ai#ai#cli#duckdb#hermes#hermes-agent#llm#ml#openclaw#python

Add a `--dry-run` flag to `tjb run` and `tjb agent` 1 day ago

good first issue

Metabuilder-Labs/tokenjam-bench

11

Comprehensive benchmarking and evaluation framework for TokenJam

Python

#agentic-ai#ai#cli#duckdb#hermes#hermes-agent#llm#ml#openclaw#python

Open Issues Need Help