Releasesby IbisMore prime-agent releases
Every prime-agent releaseprime-agent 0.9.0
- Fixed background (unattributed) kernel output missing from the expanded IPython cell view: it is now surfaced in the tool details and rendered under a "background output (unattributed)" label after stdout/stderr/result.
prime-agent 0.8.0
- Fixed an OAuth login that finishes after its server was retargeted arming the old-endpoint token against the new URL: credentials are endpoint-bound at issuance, and the host and kernel only use a token bound to the configured endpoint. Breaking: generic MCP OAuth credentials stored before this release lack the binding and require one /mcp login .
prime-agent 0.7.0
Breaking Changes Changed agent messages to always use steering delivery and removed delivery-mode options from the Python, CLI, RPC, and connection APIs. Code passing mode to agent_message.send, or a delivery mode over the CLI/RPC, must drop it. Changed Changed self-updates to report the previous and new Prime Agent versions.
prime-agent 0.6.0
Breaking Changes Changed rlm(...) to return at task admission instead of waiting for the child to finish. It now yields a spawn handle (rlm_child_id, name, session_dir, model); RLMResult and its final answer, usage, and model-fallback warning are gone.
prime-agent 0.5.0
Breaking Changes Reworked session input scheduling into a single session action lifecycle and store (daemon protocol 7, schema revision 8); older clients and daemons are rejected cleanly at connect. Changed Changed large daemon session loads to stream JSONL history and avoid retaining a second full-file copy in memory.
prime-agent 0.4.0
Breaking Changes Replaced the recursive daemon get_session_tree response with flat nodes linked by parentId (protocol 6); clients must support the new response shape. Removed /resume and bare --resume; browse sessions with left-arrow from a daemon chat, or use --resume for a direct resume.
prime-agent 0.3.0
- Changed daemon and headless execution to isolate each root session tree in a recoverable worker process, with protocol-v2 chunked snapshots, compact streaming, attachment-local backpressure, session leases, and unchanged print, JSON, and RPC interfaces.
prime-agent 0.2.0
- Improve diffs and traces: show edit diffs in the collapsed IPython view, and make trace uploads observable and resilient with logging, endpoint reporting, and retry on transient failures. Support images in context: paste images straight into the prompt, with validation, resizing, and graceful handling on non-vision models.
Also shipped on Oct 9, 2026
Prime Intellect in October 2026Google Workspace connector is available in Beta
The managed Google Workspace connector is now available in Beta in Databricks Lakeflow Connect. Use the connector to ingest audit activity from Google Workspace applications and services into Databricks. The connector uses OAuth user authorization and supports incremental ingestion.
Agentic Marketplace Discovery (Public preview)
Agentic Marketplace Discovery is now available in public preview. On the public Snowflake Marketplace Discover page in Snowsight, you can switch between Agentic discovery and Marketplace search . Describe what you need to CoCo to find and compare matching listings, or search for providers and listings directly.
All AI Gateway models with prepaid credits, backend features with your coding agent, and new ways to send feedback release - Oct 09, 2026
All AI Gateway models now available with prepaid credits. You don't need to request access to frontier models in the Neon AI Gateway anymore. If you're on a pai...
Use request tags in Unity Gateway service policies (Beta)
Custom service policies in Unity Gateway can now check caller-supplied request tags, such as requiring a tag before a model request or MCP tool call proceeds. See Request tags .
Use OpenJev as the evaluator for LLM-as-a-judge service policies (Beta)
You can now select OpenJev (Qwen3.5 4B) as the evaluator model service of a custom LLM-as-a-judge service policy. OpenJev classifies content without generating output tokens, so it typically responds faster than a chat evaluator. See Use OpenJev as the evaluator .
Code execution in Genie One (Public Preview)
Genie One can now run code in a secure, isolated sandbox to take on work that goes beyond SQL, such as more advanced analyses. Code runs on your behalf using your existing permissions, so Unity Catalog governance and data access controls continue to apply. See Code execution in Genie One .