Amp rolls out rebuilt Neo CLI

// 138d agoPRODUCT UPDATE

Amp rolls out rebuilt Neo CLI

Amp, the coding agent from Sourcegraph, is starting to roll out a rebuilt CLI codenamed Neo. The update shifts the terminal experience toward a more remote-controllable, compaction-first workflow with queued messages, plugin support, automatic context management, and a new permissions model. It also removes older features like handoff, rollback-on-edit, custom themes, and manual bash invocation, framing the release as a reset for how frontier coding agents should work in 2026.

// ANALYSIS

Big directional update, not just a feature drop. Amp is betting that modern agents should do more of the orchestration themselves, and the CLI is being reshaped around that assumption.

–Remote control from the web is the clearest new capability and makes the CLI feel less like a local-only tool.
–Auto-compaction is a real usability win for long threads and removes a bunch of manual babysitting.
–The Plugin API is strategically important because it turns permissions, tools, and UI into extensibility points.
–The product is also intentionally deleting old workflows, which is risky but coherent if the goal is to stay aligned with frontier-model behavior.
–Performance claims are meaningful here because long-thread agent UIs often get sluggish in practice.

// TAGS

ampsourcegraphai-codingcoding-agentclidevtoolautomationpluginspermissionsremote-control

DISCOVERED

138d ago

2026-05-06

PUBLISHED

138d ago

2026-05-06

RELEVANCE

9/ 10

AUTHOR

AmpCode

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

BENCHMARK1h ago

Jev 1.13 beats Cohere, Voyage in latency

Michael Chomsky shared latency benchmark results comparing TypeSafe AI's Jev 1.13 model against leading dedicated rerankers for search and retrieval pipelines. In the test, Jev 1.13 registered the fastest speeds with a 149 ms median and 205 ms p95 latency, beating Cohere v3.5 (176 ms median / 357 ms p95), Voyage 2.5 Lite (183 ms median / 232 ms p95), and Cohere 4 Fast (183 ms median / 824 ms p95).

MODEL1h ago

Tripo3D P2 lands on fal with decoupled controls

Tripo3D has launched its P2 model on fal, providing fast API-driven text-to-3D and image-to-3D textured mesh generation for creators and developers. The model introduces four texture-quality tiers, decoupled seeds for geometry and texture to facilitate fine-grained iterative design, and support for removing baked-in lighting via the v3.5 texture model for seamless integration into real-time 3D pipelines.

MODEL2h ago

TypeSafe AI has launched Jev, a "System One" AI model designed to make fast, structured decisions for software automation.

Jev is a new frontier model developed by TypeSafe AI that focuses on making structured, probabilistic decisions instead of generating free-form text. Dubbed a "System One" model, it excels at rapid judgments like routing, scoring, and data extraction, delivering typed responses with calibrated confidence levels in just 70 to 500 milliseconds. This approach allows developers to seamlessly integrate AI decisions directly into their code logic with dramatically lower latency and cost than traditional LLMs.