> This page is for NeMo Fabric, version v0.4.0.
> For other versions, use one of these documentation indexes:
> - Latest (v0.4.0) (default): https://docs.nvidia.com/nemo/fabric/latest/llms.txt
> - dev: https://docs.nvidia.com/nemo/fabric/dev/llms.txt
> - v0.5.0: https://docs.nvidia.com/nemo/fabric/v0.5.0/llms.txt
> - v0.4.0: https://docs.nvidia.com/nemo/fabric/v0.4.0/llms.txt
> - v0.3.0: https://docs.nvidia.com/nemo/fabric/v0.3.0/llms.txt
> - v0.2.0: https://docs.nvidia.com/nemo/fabric/v0.2.0/llms.txt
> - v0.1.1: https://docs.nvidia.com/nemo/fabric/v0.1.1/llms.txt
> - v0.1.0: https://docs.nvidia.com/nemo/fabric/v0.1.0/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/fabric/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/fabric/_mcp/server.

# Release Notes

> Review the current NVIDIA NeMo Fabric release status and find the official release history.

This page summarizes the current documentation-visible release state. GitHub
Releases remain the source of truth for complete release history and
tag-specific notes.

## Current Release

NVIDIA NeMo Fabric 0.4 adds adapters for Cline, OpenClaw, OpenCode, and Qwen
Code. It also adds a shared-service lifecycle for adapters that support it,
extends Pi observability with NeMo Relay telemetry and streaming, and supports
normalized model sampling and token-limit settings.

For release artifacts and the complete change history, refer to
[GitHub Releases](https://github.com/NVIDIA/NeMo-Fabric/releases).

## Upgrade Notes

> **Warning**
>
> Relay-enabled integrations in NeMo Fabric 0.4 require NeMo Relay `>=0.9,<0.10`.
> Upgrade separately installed Relay Python packages and `nemo-relay` CLI
> installations before using Relay with 0.4 adapters. The published Hermes Agent
> v2026.9.24 release requires Relay 0.8, so Hermes Relay telemetry and streaming
> currently require the compatible, merged Hermes Relay 0.9 revision in a
> separate Python 3.14 environment. Ordinary Hermes Agent invocations do not
> require that development checkout.

The public Rust `ModelConfig` and `AgentModelConfig` structs now include
optional `top_p` and `max_tokens` fields, and `RuntimeHandle` includes an
optional `service_id`. Applications that construct these structs with explicit
Rust struct literals must add the new fields or use a constructor or default
that supplies them. Existing serialized configurations can omit the new fields.

## Release Highlights

### More Harness Integrations

* [Cline](/nemo/fabric/integrations/harness-integrations/cline) runs a local Cline SDK session
  across ordered invocations and maps supported model, tool, skill, and MCP
  configuration.
* [OpenClaw](/nemo/fabric/integrations/harness-integrations/open-claw) can run a Gateway for one
  runtime or connect multiple runtimes to a shared Gateway.
* [OpenCode](/nemo/fabric/integrations/harness-integrations/open-code) runs an embedded OpenCode
  host and persistent session. The adapter can return a patch artifact for
  files changed during an invocation.
* [Qwen Code](/nemo/fabric/integrations/harness-integrations/qwen-code) runs the Qwen Code SDK and its
  bundled CLI in an isolated child process, reusing one session across ordered
  invocations.

### Shared Adapter Services

The [Python SDK](/nemo/fabric/sdk/python-sdk#shared-services) now exposes
`Fabric.prepare_service()` for a NeMo Fabric-managed service and
`Fabric.attach_service()` for a service managed by another system. Multiple
runtimes can use one service while keeping separate runtime IDs and harness
sessions. OpenClaw supports both service paths. Service handles are local to
the creating process and cannot be used for cold resume.

### Relay and Model Configuration

The [Pi adapter](/nemo/fabric/integrations/harness-integrations/pi) now emits Relay telemetry and
supports live ATOF records through `Runtime.invoke_stream()`. Pi streaming
uses the embedded collector; its Relay 0.9 extension and CLI must be installed
separately. Pi model telemetry also depends on a supported model API and a
matching Relay gateway upstream.

The normalized model configuration now accepts `models.<role>.top_p` and
`models.<role>.max_tokens`. Adapters use these fields when their descriptors
declare support; unsupported settings fail during planning. See the
[Python SDK guide](/nemo/fabric/sdk/python-sdk) and the selected adapter guide for the
exact mapping and limits.

The [Deep Agents adapter](/nemo/fabric/integrations/harness-integrations/lang-chain-deep-agents) also adds an
opt-in local shell backend for supervised demonstrations. This backend runs
commands with the adapter host user's permissions and provides no process
isolation.

## Current Limitations

The current release has the following limitations:

* Provider-backed third-party adapter registries are not included.
* An automated adapter conformance suite is not included.
* Cancellation, live updates, and cold resume are not exposed as supported
  adapter lifecycle operations. Shared service handles cannot be persisted
  across processes.
* The [Remote Agent adapter](/nemo/fabric/integrations/harness-integrations/remote-agent) does not
  normalize the remote service's MCP, skills, tool policy, or subagents. Relay
  streaming requires a separately instrumented remote service and a collector
  reachable by that service and NeMo Fabric.
* The new Cline, OpenCode, and Qwen Code adapters do not support Relay
  telemetry or native streaming. Consult each adapter guide for other
  capability limits.