A developer built Spellbook of Skill, an MIT-licensed collection of development tutorials and guides organized by category and difficulty, as a companion to the earlier Spellbook of Prompt. The projec…
Amika co-founder and CEO Dylan Mikus argued in a September 13th thread on X that cloud coding agents should reuse persistent virtual machines instead of rebuilding a clean environment for every pull r…
Z.ai released GLM-5.3-Flash on August 26, 2026, a 320-billion-parameter open-weight Mixture-of-Experts model that activates only 18 billion parameters per token and supports a one-million-token contex…
Independent researcher and MCA graduate MadB0i is seeking an arXiv cs.CR endorsement for a first paper, "KavachBench: An Empirical Evaluation of Deterministic Policy Enforcement Against Issue-Based Pr…
GitHits launched infrastructure to discover open-source code and verify how it behaves, arguing that coding agents must read code to make engineering decisions even inside automated software factories…
Digital Applied published a six-signal taxonomy on September 21, 2026 for determining whether an AI model launch is imminent, requiring each signal to be verifiable via a public URL and a named field.…
Typemill released version 2.27.0, adding the Soloprint theme for publishing a single web book with accompanying PDF and EPUB editions, plus AI adapter improvements, translation robustness fixes, and s…
A coding agent marketed as the fastest available claims to run more than 5x faster than Codex, according to promotional material for the tool. The agent is powered by OpenCode and is pitched at "high …
A developer who maintains Alca, a provider-tracking site, documented four distinct categories of "free" AI model quotas after repeatedly exhausting paid tiers: harness-locked pools usable only through…
Coding agents fail more often at the file-system boundary than at reasoning, according to an analysis of how Aider, Claude Code, Cursor, OMP, DeepSeek Harness, OpenCode, and Morph write code to disk. …
A developer published a configuration guide for setting up OpenCode V2 with a single custom provider, Relax AI (Beta), authenticated via a saved account rather than environment variables or shell API …
Agnostic-ai v0.62.0 now translates portable allow, deny, and ask permission policies to OpenCode and Kilo Code project configuration, and unsupported policy mappings produce a coverage note instead of…
A developer released jev, a zero-dependency Python CLI and library that wraps TypeSafe's Jev decision model so coding agents like Claude Code, Codex, and OpenCode can classify, filter, rank, or verify…
Developer al3rez released colm, an MIT-licensed Linux terminal workspace manager for coding agents built as a fork of the Ghostty terminal, according to a Show HN post. colm adds a workspace sidebar, …
A developer implemented a 6502 microprocessor emulator written in Markdown and executed it using OpenCode with the GLM 5.1 model running on Grunden.ai, following earlier experiments with a user-space …
LetMeSend.Email launched an MCP server at mcp.letmesend.email that exposes 35 tools for mailbox management, email sending, domain health, and campaign handling to AI agents. The server supports OAuth …
A developer built a model router for OpenCode that uses the TypeSafe AI Jev model via OpenRouter to classify coding tasks by coordination, uncertainty, and consequences, then routes each request to ei…
Agnostic-ai released version 0.61.0, which now emits Cline rules to the `.clinerules/` directory that Cline's CLI and editors read. The release also makes invalid OpenCode and Junie names fail before …
Anthropic paused changes to Claude Agent SDK usage as of June 15, stating that Claude Agent SDK, claude -p, and third-party app usage still draw from a subscription's usage limits and that the previou…
A September 18, 2026 guide ranked 11 open-source agent harnesses for local LLMs by OSI-approved license, documented local runtimes, maintenance status, and safety controls, with OpenCode taking the to…