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.
Also shipped May 21, 2026Prime Intellect in May 2026 →
Replit Enterprise, Now Self-Serve
Replit Enterprise is now available for direct purchase through the website. Organizations can configure SSO and SCIM and provision accounts without needing to go through a sales demo or contract negotiation.
Billing - Modernized Billing Profile with new payment options
The Billing Profile now has a modern UI and a single space that unifies billing information, payment method management and an enhanced subscriptions view under a single Subscriptions tab. What changed The Subscriptions tab brings billing information, payment method management, and your subscriptions together in one place.
Build Plugins: End of support for Node.js 18 + Node.js 20
The following versions of Node.js have reached their official end of life: Node.js v18 on April 30, 2025 Node.js v20 on April 30, 2026 Now it’s time to say goodbye to Node.js versions 18 and 20 in our build plugins. This change will allow us to use...
AI Conversations Now in Open Beta
Conversations is now in open beta for all Sentry users. It gives you a readable view into past sessions with your agent, showing the full exchange of messages and tool calls so you can understand exactly what happened during each session.
Shopify CLI 4.0: SemVer, auto-updates, removing deprecated flags and commands
The release of Shopify CLI 4.0 today brings clarity to CLI versioning, the introduction of automatic updates, and the announced removal of the deprecated --force flag from shopify app deploy . Semantic Versioning Shopify CLI is now following semantic versioning practices.
FLUX Erase , Remove Anything, Leave No Trace
A new FLUX Tools endpoint for clean, prompt-free object removal. Provide an image and a binary mask; the model removes the masked content and reconstructs the scene coherently.
More from prime-agentEvery prime-agent release →
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.
prime-agent 0.0.1
Initial Prime Agent release, forked from pi-mono. Add a persistent IPython tool backed by a Jupyter kernel so Python state survives across tool calls, and make it the default tool set. Add recursive RLM subagents: IPython code can spawn child agent sessions via rlm.run, with a compact tray, full child transcripts, and aggregated usage.
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 0.0.7
- 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.
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 0.0.10
- 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.