# tensorzero

> TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.

- **URL**: https://www.freshcrate.ai/projects/tensorzero
- **Author**: tensorzero
- **Category**: Infrastructure
- **Latest version**: `2026.6.0` (2026-06-04)
- **License**: Apache-2.0
- **Source**: https://github.com/tensorzero/tensorzero
- **Homepage**: https://tensorzero.com
- **Language**: Rust
- **GitHub**: 11,261 stars, 819 forks
- **Registry**: github
- **Tags**: `ai`, `ai-engineering`, `anthropic`, `artificial-intelligence`, `deep-learning`, `genai`, `generative-ai`, `gpt`, `rust`

## Description

TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `2026.6.0` | 2026-06-04 | High | > [!CAUTION] > **Security Advisory** > > This release fixed a high-risk vulnerability affecting the TensorZero Gateway. > > Please refer to the security advisory for more details: https://github.com/tensorzero/tensorzero/security/advisories/GHSA-824w-x939-6cmc |
| `2026.5.2` | 2026-05-20 | High | **New Features**  - Accept both strings and array of strings for `stop` in the OpenAI-compatible inference endpoint (thanks @pragnyanramtha). - Emit additional OpenInference attributes for Arize compatibility. |
| `2026.5.1` | 2026-05-15 | High | **Bug Fixes**  - Treat SSE body decoding errors as fatal. |
| `2026.5.0` | 2026-05-08 | High | > [!CAUTION] > **Breaking Changes** > > - The UI will now require authentication when the gateway requires authentication. Previously, the UI only required authentication for gateway usage.  **New Features**  - Improve error handling (e.g. status code propagation) and logging for complex streaming inferences (e.g. fallbacks).  _& multiple under-the-hood and UI improvements (thanks @arisp)_ |
| `2026.4.1` | 2026-04-24 | High | > [!CAUTION] > **Breaking Changes** > > - The gateway now defaults to async observability writes to reduce tail latency: inferences are sent to the client before they are persisted in the database. To restore the previous behavior, set `observability.async_writes = false`. **[[docs]](https://www.tensorzero.com/docs/gateway/configuration-reference)**  > [!WARNING] > **Deprecations** > > - Removed the TensorZero Autopilot "Sessions" page from the UI. We recently added a TensorZero MCP that |
| `2026.4.0` | 2026-04-02 | High | **New Features**  - Add an MCP server to the gateway exposing its API in `/mcp`. - Report provider prompt caching statistics via API and UI. - Report usage statistics (e.g. tokens, latency, cost) for inference evaluations via CLI tool, API, and UI. - Add the Prometheus metrics `tensorzero_input_tokens_total` and `tensorzero_output_tokens_total`. - Add configuration field `content_type_overrides` to handle file inputs for long-tail providers.  _& multiple under-the-hood and UI improvement |
| `2026.3.4` | 2026-03-26 | Medium | > [!WARNING] > **Planned Deprecations** > > - The configuration for inference evaluations should be nested under the relevant functions moving forward **[[docs]](https://www.tensorzero.com/docs/evaluations/inference-evaluations/tutorial)**. You can run evaluations by providing a function name and a list of evaluators. The legacy format will be removed in a future release. >   ``` >   [functions.write_haiku.evaluators.exact_match] >   type = "exact_match" >   ``` > - The legacy implementa |
| `2026.3.3` | 2026-03-18 | Low | **Bug Fixes**  - Fixed two edge cases affecting batch inference. - Fixed a UI bug affecting "Try with..." with inputs that include base64 files. - Removed assistant message prefill for JSON functions + Anthropic (deprecated by Anthropic).  **New Features**  - Added an implementation of GEPA (automated prompt engineering) based on durable workflows. - Allow users to specify duplicate tool calls in `all_of` tool evaluators to evaluate parallel tool calling. - Allow users to specify an ex |
| `2026.3.2` | 2026-03-13 | Low | **Bug Fixes**  - Fixed an UI issue that prevented certain pages from rendering when depending on historical configuration.  **New Features**  - Added Postgres as an alternative observability backend to ClickHouse. Postgres is the simplest way to get started; we recommend ClickHouse if you're handling >100 RPS. - Added the `openrouter::xxx` short-hand for embedding models. - Added support for per-session API keys in the browser (instead of a global environment variable) when auth is enabl |
| `2026.3.1` | 2026-03-05 | Low | > [!WARNING] > **Completed Deprecations** > > - Removed the deprecated `model_provider_name` filter for `extra_body` and `extra_headers`. Please use `model_name` and `provider_name` instead. > - Removed the legacy experimental `list_inferences` endpoint and method. Please use the new endpoint instead. **[[docs]](https://www.tensorzero.com/docs/observability/query-historical-inferences)** > - Removed several long-deprecated types and methods from the TensorZero Python SDK.  > [!WARNING] > |

## Citation

- HTML: https://www.freshcrate.ai/projects/tensorzero
- Markdown: https://www.freshcrate.ai/projects/tensorzero.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/tensorzero/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._