Amp added a "Plaid" speed tier for modes using GPT-6 Astra, running inference requests up to 6× faster than normal requests at 6× the cost per token. The tier is selected in the new thread dialog's mo…
Amp, the agentic coding tool from Sourcegraph, is now free to use for customers who bring their own compute and model subscriptions or API keys, with users paying only for orbs or running agents free …
Amp now lets users choose the models behind its builtin modes and add their own custom agents to the Dial, with two tabs in Settings → Mode Dial for configuration. The Tune Modes tab lets users set th…
Amp is removing the sidebar from its TUI (terminal user interface) to push users toward its native and web apps, which offer more powerful sidebars for managing multiple threads from orbs, runners, an…
Amp, the coding agent and development environment company, introduced orbs, remote agents that run in cloud-based virtual machines and can be controlled from the web, phone, or CLI. Orbs support porta…
Ampcode.com now supports connecting remote Model Context Protocol (MCP) servers via Streamable HTTP with OAuth or Bearer tokens, enabling use of MCP-provided tools in orbs, the TUI, and Puck. Personal…
Amp is offering students and teachers a discounted subscription at $10 per month, half the usual price, which includes access to its frontier agent, remote machines called orbs, unlimited code hosting…
Puck now supports realtime voice chat, powered by gpt-realtime-2.1, which delegates work to the Puck agent running on GPT-5.6 Sol and summarizes responses aloud while full text appears in the thread. …
Amp, a 20-person software company, has achieved SOC 2 compliance without using pull requests, a practice its auditors confirmed is not required by the standard. The company's controls include restrict…
Amp changed its Dial feature so that linking a ChatGPT subscription routes all low, medium, and high modes exclusively to OpenAI models billed to the subscription, eliminating credit charges for those…
Amp shipped the Dial two weeks ago, changing the default model from Claude Opus 4.8 to GPT-5.6 Sol, and 69% of Dial users never switched from the medium setting. The company received zero complaints d…
Amp's agents can now set their own schedules and wake themselves up, continuing with full context and history. Users can schedule agents to perform tasks like monitoring database queries, checking on …
Amp launched Amp Subscriptions in Beta, offering monthly pricing with cheaper and more predictable rates, including bonus 2x usage for orbs and agents in the first month for subscribers who join by Ju…
Amp replaced its named agent modes (smart, deep, rush, large) with a dial offering low, medium, high, and ultra settings, each backed by specific models and reasoning efforts. The change simplifies mo…
Amp rewrote its read_thread tool to handle long threads, which can now exceed 21 million tokens due to compaction. The new version uses a subagent with GLM 5.2 to extract information more accurately, …
Amp launched remote 'orbs' that let AI agents run unsupervised on cloud machines with 32GB memory and 16 cores for $1.66/hour, enabling developers to spawn and manage multiple agents from the same int…
Amp announced a new feature allowing users to create custom agents via plugins, which can serve as main agents, subagents, or worker agents with custom orb colors. The Plugin API provides primitives f…
Ampcode's Librarian AI agent is now approximately three times faster and 43% cheaper after switching to OpenAI's GPT-5.5 model with websocket mode, reducing average search latency from 237 seconds to …
Amp introduces a new diff review feature that allows users to review code changes from agent-generated threads on desktop or mobile, with duplicate block detection to reduce cognitive load. The featur…
Amp announced that its 'deep' and 'rush' modes now deliver first tokens 87% faster and overall responses 32% faster, achieved primarily through websocket communication with OpenAI and a recent platfor…