prime-agent 0.0.7
- Add Python-backed skills that install into the persistent IPython kernel and appear alongside markdown skills. Add Prime team selection during Prime Inference login so team inference costs use the selected Prime CLI context. Guide unauthenticated users through login and model selection before the first agent turn.
Also shipped Jun 1, 2026Prime Intellect in June 2026 →
Fivetran CLI enters beta, Connect Card gains all_fields parameter
The beta Fivetran CLI manages accounts, connections, schema settings and users and helps develop custom connectors from the terminal. Connect Card's all_fields option shows setup fields hidden by default.
Unlocking a New Way to Build Enterprise Data Apps with Microsoft Fabric
Replit and Microsoft have collaborated to allow developers to build AI-powered applications in Replit and deploy them directly into Microsoft Fabric with enterprise governance.
May Release Spotlight
OpenRouter has released new speech and transcription APIs, Model Fusion, private models, and enterprise workspace controls, alongside 20 new model launches.
Protect apps in the new app builder
Live on cloud • Enterprise Public beta Apps created with the new app builder can now be protected and checked into your chosen Source Control Manager (SCM). Source Control lets organizations manage changes using remote SCM providers GitHub, GitLab, AWS CodeCommit, Bitbucket, and Azure Repos.
Customize RPID values for Passkeys GA
Boost Passkey adoption by enabling shared enrollment across subdomains. You can now customize the RP ID to allow a single Passkey to authenticate users across multiple applications under the same root domain. Now GA!
Fivetran Connector SDK 2.9 logs peak memory and adds Copilot plugins
Version 2.9.2 makes fivetran debug log peak memory usage and adds validation in fivetran init, and 2.9.1 lets fivetran init use Copilot plugins for AI-assisted connector development.
More from prime-agentEvery prime-agent release →
prime-agent 0.0.9
Release packaging fix; no functional changes.
prime-agent 0.0.8
- Fix the onboarding flow so model selection, manual key entry, and cancellation all resolve correctly instead of re-prompting on every launch. Add a Prime Inference onboarding splash for Prime CLI users and persist an onboarding-completed flag.
prime-agent 0.0.6
- Polish installer startup so npm and Node.js setup stays behind the Prime splash with rotating progress detail. Read Prime Inference credentials from the Prime CLI config so prime login makes Prime Inference models available on startup. Skip a saved default model at startup when it no longer has configured auth, avoiding stale unauthenticated selections.
prime-agent 0.0.5
- Redesign onboarding: guide unauthenticated users through login and model selection before the first turn, with a refreshed Prime splash and centered menu surfaces. Add a Prime Inference login dialog with browser sign-in and a manual API-key fallback. Adapt interactive surfaces and the editor background to the detected terminal colors (dark vs light).
prime-agent 0.0.10
- Add Claude Opus 4.8 to Prime Inference, with reasoning support. Adopt the upstream IPython control-environment prompt: prefer %%bash cells and run project imports and tests through the project's own environment. Rework Ctrl+C to interrupt first and exit on a second press, with Escape now clearing the input bar.
prime-agent 0.1.0
- Add a daemon-backed Agents View as the default local entrypoint, with daemon mode and CLI controls for creating, listing, attaching, killing, renaming, and prompting live sessions. Add an AgentConnection client boundary with in-process and daemon adapters, plus versioned daemon protocol metadata and attach snapshots for future Swarm wrapping.
prime-agent 0.0.4
- Add a system prompt note listing the pre-installed Python packages (requests, httpx, pandas, numpy, scipy, pydantic, and more). Add a default extra-packages constant and kernel bootstrap that installs those packages, with the prompt referencing the constant instead of a hardcoded list.
prime-agent 0.0.2
- Add a persistent IPython tool backed by a Jupyter kernel, with an auto-bootstrapped uv-managed Python runtime, so variables and imports survive across tool calls. Add the RLM harness and prime-agent-runtime bridge so IPython code can spawn recursive child agent sessions via rlm.run, with subagent tray, detail views, and chat-style child transcripts.