Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Evaluation and Tracking for LLM Experiments and AI Agents
| Date | Stars |
|---|---|
| 2026-07-31 | 3474 |
| 2026-08-03 | 3474 |
| 2026-08-04 | 3482 |
| 2026-08-06 | 3482 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
35.0
growth rate 0.00%/day
 [](https://dev.azure.com/truera/trulens/_build/latest?definitionId=8&branchName=main)   [](https://snowflake.discourse.group/c/ai-research-and-development-community/trulens/97) [](https://www.trulens.org/getting_started/) [](https://colab.research.google.com/github/truera/trulens/blob/main/examples/quickstart/quickstart.ipynb) [](https://deepwiki.com/truera/trulens) # 🦑 TruLens  **TruLens finds where your agent fails and where you can cut cost without losing quality.** Open source, OpenTelemetry-native. Instrument any app with a decorator, score every step with LLM judges that explain themselves, then compare versions and ship the one that earns it. Tracing is OpenTelemetry-native, so a trace is portable to any OTLP backend, and evaluations run either as traces land or over a dataset after the fact. Read more about the core concepts behind TruLens including [Metrics](https://www.trulens.org/getting_started/core_concepts/feedback_functions/), [the RAG Triad](https://www.trulens.org/getting_started/core_concepts/rag_triad/), and [Honest, Harmless and Helpful Evals](https://www.trulens.org/getting_started/core_concepts/honest_harmless_helpful_evals/). ## Trace every step Latency, inputs, outputs, tokens and cost, recorded per step, so a bad answer has a traceable cause rather than a vibe.  ## Compare versions, ship the frontier Scores, latency and cost per app version, so the tradeoff is visible instead of guessed. The cheapest version is often not the worst one.  ## Don't take our word for it TruLens judges are graded against human annotations, out of the box. | Result | Metric | Detail | |--------|--------|--------| | **95%** | Agent errors caught with Agent GPA on TRAIL/GAIA | 267 of 281 human-annotated errors, against 55% for the baseline trace judge ([arXiv:2510.08847](https://arxiv.org/abs/2510.08847)) | | **0.81** | Groundedness F1 on LLM-AggreFact | Ahead of a fine-tuned proprietary model, Bespoke-MiniCheck-7B, on F1, precision and recall over an 11,000-example holdout ([RAG triad benchmarks](https://www.snowflake.com/en/engineering-blog/benchmarking-LLM-as-a-judge-RAG-triad-metrics/)) | | **0.93** | Context relevance NDCG@5 | First of five tools on three of four ranking metrics, ahead of WandB Weave, RAGAS, DeepEval and UpTrain ([AIMultiple, 23 March 2026](https://aimultiple.com/rag-evaluation-tools)) | | **4.2:1** | Context relevance adversarial win-loss | Scored the correct passage over a near-copy with one fact swapped 4.2 times for every reversal, against 3.3:1 for the next best tool ([AIMultiple](https://aimultiple.com/rag-evaluation-tools)) | ## Adopted by AI teams at Walmart Global Tech, Cisco, J.P. Morgan Chase, Equinix, VMware by Broadcom, Hitachi Digital Services, Thomson Reuters, phData, HID Global and others. See [ADOPTERS.md](https://github.com/truera/trulens/blob/main/ADOPTERS.md). ## Installation and Setup Install the trulens pip package from PyPI. ```bash pip install trulens ``` Install with a specific LLM provider for feedback evaluation: ```bash pip install trulens trulens-providers-openai # OpenAI / Azure OpenAI pip install trulens
Excerpt of 8,579 characters
Read on GitHub
229
222
222
Piotr Mardziel · United States
203
172
134
corey hu · @snowflakedb · United States
113
73
54
35
34
26
24
corey hu · @facebookresearch · United States
22
18
18
14
10
10
10
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2dcc7cf80631b27e, topic:llm-evaluation, topic:llm-eval
matched fp:2dcc7cf80631b27e, topic:llmops
matched fp:2dcc7cf80631b27e, topic:ai-agents, desc:ai agents