Bento Term, a native tmux client for macOS, iPhone, and iPad, has been released as open-source under Apache-2.0, featuring agent states for ten AI coding agents and voice input. The app, which require…
Amp, a coding-agent company led by CEO and co-founder Quinn Slack, obtained SOC 2 Type II certification while allowing engineers to push code directly to the main branch without mandatory pull request…
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…
FreeBuff, the ad-supported build of Codebuff launched on 12 February 2026, runs small text-only ads between agent turns and may analyze prompts to personalize them, while Clixad, built by the author, …
A developer explains the current state of coding agent context files, noting that AGENTS.md has become an open, vendor-neutral standard backed by OpenAI, Google, and the Linux Foundation's Agentic AI …
A backend engineer who spent one week using LLM agents for coding and review found that 80 of 730 Claude Code sessions involved direct human input, while 650 were agent-initiated, and Codex ran more s…
Centaur 2.0, announced by Paradigm, introduces company-wide context archival, granular permissions, and MCP support, enabling agents to access tools and data across platforms. Over 80% of Centaur sess…
Developer Adam Wathan predicts that within six months, AI coding models will become commoditized, comparing them to gas at a gas station. Amp, an AI coding tool, has switched its default model from Op…
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…
GitHub began using interaction data from Copilot Free, Pro and Pro+ to train its models unless users opt out, effective April 24, 2026, while Business and Enterprise plans are unaffected. The change i…
Book-to-skill, an MIT-licensed tool with 15,259 GitHub stars, converts technical books, document folders, or paper stacks into structured Agent Skills (SKILL.md plus per-chapter files) for Claude Code…
A new open-source project, readable-ad-hoc-commands, formats AI coding agents' shell commands into readable scripts with named values, comments, phase banners, and plain-English summaries, aiming to r…
Free AI coding tiers are advertised in units that cannot be converted into actual work, as one agent task involves about a dozen model calls and sends 348,600 input tokens, not the 144,000 a naive est…
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…
A developer released the Thorsten Prompt, a Claude Code Agent Skill that grades every non-trivial prompt against the Slack test and three checks (standard, information, definition of done), shows a re…
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…