Telexed

AI news through a solo-operator lens — only what changes your day19 of 843

FILTER[All][Agents & tools][Models & API][Generative media][Infra & SaaS][ASO & growth][Indie business][Idea signals][Other][★6+ high-signal]

GeekNews ✕clear filters

Fri, May 222 dispatches

#0843
#0843Agents & tools GeekNewslast week
`agentmemory`, Persistent Memory for AI Coding Agents
60radar
agentmemoryCoding agent memory tool — auto-injects context across sessions
Session context gets captured, compressed, and injected automatically. Useful when CLAUDE.md-style notes hit limits or go stale.
- Background capture records tool usage and compresses it for the next session, reducing repeated stack and architecture explanations.
- Targets a real pain in Claude Code-style workflows: local project context disappears once the session ends.
- The pitch is persistent agent memory beyond a 200-line manual note file. Worth trying on long-running codebases, with stale-memory review still needed.
Source: news.hada.io/topic?id=29754Read original →
FIG-8431:1
60radar
FIG-8431:1
#0842
#0842Agents & tools GeekNewslast week
`Herdr`, a tmux-style terminal workspace for AI agents
70radar
HerdrTerminal workspace — manages multiple coding agents in parallel
Persistent sessions, panes, and SSH support are packaged around running multiple coding agents at once. Worth a look if tmux is becoming the bottleneck.
- Keeps detach/reattach and pane splitting from tmux, so existing terminal habits still transfer.
- Targets parallel use of Claude Code, Codex, and OpenCode rather than generic shell multiplexing.
- SSH support matters for remote dev boxes; agent sessions can survive local context switches.
Source: news.hada.io/topic?id=29738Read original →
FIG-8421:1
70radar
FIG-8421:1

Thu, May 213 dispatches

#0841
#0841Agents & tools GeekNewslast week
GitHub confirms 3,800 repositories compromised via malicious `VS Code` extension
60radar
A single developer workstation became the entry point. VS Code extension trust is now part of supply-chain security, so extension audits are worth doing now.
- About 3,800 internal repositories were affected after one employee installed a trojanized VS Code extension.
- GitHub’s current assessment limits exposure to internal repositories, but compromised developer endpoints can still leak secrets and code context.
- The extension was removed from VS Code Marketplace, infected endpoints were isolated, and incident response started immediately.
- Practical takeaway: review installed IDE extensions, publisher names, permissions, and disable unused tools before they become build-chain risk.
Source: news.hada.io/topic?id=29731Read original →
FIG-8411:1
60radar
FIG-8411:1
#0840
#0840Agents & tools GeekNewslast week
Google Cloud revamps agent development with `Antigravity 2.0`
70radar
AntigravityAgent dev tool — links local prototypes to cloud execution
Google is packaging local prototyping and cloud deployment into one agent stack. If Managed Agents API removes hosting glue, it is worth tracking now.
- Antigravity 2.0 and Managed Agents API are framed as an integrated dev kit, not separate demos.
- The flow targets local prototyping first, then managed cloud execution. Less custom orchestration if the API is usable.
- The available text is short, so pricing, lock-in, and runtime limits remain unknown. Treat it as watchlist, not migration trigger.
Source: news.hada.io/topic?id=29718Read original →
FIG-8401:1
70radar
FIG-8401:1
#0839
#0839Agents & tools GeekNewslast week
`Gemini CLI` will stop working on June 18, 2026
80radar
Gemini CLITerminal AI CLI — runs Gemini from the command line
Google is folding terminal AI workflows into Antigravity CLI. A popular CLI with 100k+ GitHub stars now has a hard migration deadline, so scripts and habits need cleanup soon.
- Gemini CLI grew to millions of users, 100k+ GitHub stars, and 6,000+ merged PRs; this is not a small side-tool shutdown.
- Google is consolidating capability into Antigravity CLI, pointing its agent tooling toward multi-agent workflows rather than a standalone Gemini terminal client.
- The deadline is June 18, 2026. Any local aliases, CI helpers, docs, or onboarding snippets using Gemini CLI should be replaced before then.
Source: news.hada.io/topic?id=29711Read original →
FIG-8391:1
80radar
FIG-8391:1

Wed, May 204 dispatches

#0838
#0838Agents & tools GeekNewslast week
`Codex Relay` Adds Mobile Terminal, Browser, Git, File Viewer, and Markdown for Codex
50radar
Codex RelayMobile Codex companion — adds terminal, Git, and file viewer
A free OSS companion fills gaps around mobile Codex use. The overlap with official remote access caps urgency, but the extra tools make it worth a quick trial.
- Includes Terminal, Browser, Git, File Viewer, and Markdown in one mobile-focused Codex companion.
- Official Codex Remote already covers the core use case, so this is a convenience layer rather than a must-migrate tool.
- Open-source and free lowers trial cost; check auth, repo access, and maintenance before using it on private work.
Source: news.hada.io/topic?id=29706Read original →
FIG-8381:1
50radar
FIG-8381:1
#0837
#0837Agents & tools GeekNewslast week
GitHub Internal Repos Accessed After Employee Device Compromise
40radar
A poisoned VS Code extension became the entry point. Treat editor extensions as supply-chain risk, not convenienceware.
- Attack path: a compromised employee endpoint via malicious VS Code extension, followed by access to internal repositories.
- GitHub removed the malicious extension version and isolated the endpoint. Extension version pinning and review matter for dev machines.
- No concrete customer-impact detail is available in the provided text. Actionable takeaway stays limited to workstation hardening.
Source: news.hada.io/topic?id=29703Read original →
FIG-8371:1
40radar
FIG-8371:1
#0836
#0836Agents & tools GeekNews2 weeks ago
`Cursor Composer 2.5` becomes Cursor's most-selected model, with **10x** usage bonus
80radar
CursorAI coding IDE — agentic code writing and edits
The in-house coding model is overtaking third-party defaults inside the IDE. Test it today while the usage cap is temporarily loose.
- CEO Michael Truell said Composer 2.5 became the most-selected model in Cursor; adoption moved fast right after launch.
- All users get 10x usage for one day, making it a low-cost window for real project testing instead of toy prompts.
- This is pressure on Claude and OpenAI workflows: IDE-native models win when latency, quota, and UX beat raw benchmark trust.
Source: news.hada.io/topic?id=29691Read original →
FIG-8361:1
80radar
FIG-8361:1
#0835
#0835Agents & tools GeekNews2 weeks ago
`Mirage`, a unified virtual filesystem for AI agents
70radar
MirageVirtual filesystem for AI agents — mounts SaaS as one tree
Different SaaS backends become one filesystem tree. Agents can use Unix tools instead of learning every SDK or MCP, so cross-service automation gets simpler.
- Mounts S3, Google Drive, Slack, Gmail, and Redis into one filesystem tree — fewer integration surfaces for agents.
- Agents can work through Unix-style bash tools, reducing the need to teach each agent service-specific SDKs or MCP interfaces.
- Cross-service pipelines become file operations. Moving data between storage, chat, mail, and cache can be scripted more cheaply.
Source: news.hada.io/topic?id=29681Read original →
FIG-8351:1
70radar
FIG-8351:1

Tue, May 195 dispatches

#0834
#0834Agents & tools GeekNews2 weeks ago
`Goal Setter`, an agent skill for writing safer `Codex` goals
50radar
Goal SetterCodex agent skill — interviews users to define done states
Long-running agent work now needs sharper stop conditions. This skill turns vague requests into explicit done states before Goal burns time and tokens.
- Goal Setter interviews the user before creating a goal, reducing drift in long Codex runs.
- The core check is what exact state counts as done. Without that, Goal can waste tokens fast.
- Useful for large refactors, test work, or migration tasks where the agent needs persistence but clear boundaries.
Source: news.hada.io/topic?id=29661Read original →
FIG-8341:1
50radar
FIG-8341:1
#0833
#0833Agents & tools GeekNews2 weeks ago
Anthropic Acquires `Stainless` to Expand Agent Tooling
50radar
StainlessAPI tooling SaaS — Generates SDKs and MCP servers
Agent value now depends on how many real systems it can reach. This is not an immediate product change, but it signals broader Claude tool integration ahead.
- Stainless builds SDK and MCP server tooling, so the acquisition targets the connection layer between APIs and agents.
- The move shifts focus from model answers to action-capable agents that can touch data, tools, and workflows.
- No pricing, release date, or developer-facing feature is included yet. Treat it as a roadmap signal, not something to adopt today.
Source: news.hada.io/topic?id=29647Read original →
FIG-8331:1
50radar
FIG-8331:1
#0832
#0832Agents & tools GeekNews2 weeks ago
`Project Glasswing`: What `Mythos` Demonstrated
60radar
MythosSecurity agent — proves exploit chains automatically
The bar moved from spotting suspicious code to proving a working exploit path. This is early, but it hints at security agents that can validate bugs before a human review.
- Mythos Preview ran across 50+ Cloudflare repos, linking multiple primitives into exploit chains instead of flagging isolated bugs.
- It wrote trigger code, compiled and executed temporary tests, then revised failed hypotheses. That closes the gap between static finding and proof.
- The practical signal is security automation shifting toward reproducible evidence. Expect fewer raw alerts, more agent-generated repro cases.
Source: news.hada.io/topic?id=29645Read original →
FIG-8321:1
60radar
FIG-8321:1
#0831
#0831Agents & tools GeekNews2 weeks ago
Using Git `--author` to Block AI Bot Spam in GitHub Repos
40radar
AI-generated PR and issue noise can bury real maintainer discussion fast. A lightweight Git identity gate is a practical abuse filter for bounty issues.
- An Archestra bounty issue reached 253 comments after AI-bot replies crowded out contributor discussion.
- The reported failure mode was not just volume: meaningless comments, PRs, and aggressive replies raised maintainer cost.
- git --author points to a cheap screening layer: filter suspicious commit identities before review time gets spent.
Source: news.hada.io/topic?id=29642Read original →
FIG-8311:1
40radar
FIG-8311:1
#0830
#0830Agents & tools GeekNews2 weeks ago
Using `Codex` `Goals` for Long-Running Tasks
50radar
CodexCoding agent — continues multi-turn work toward a goal
Goals keeps multi-turn work moving toward a defined outcome. Useful for profiling, patches, benchmarks, flaky tests, and evidence-based audits.
- Goals is a persistent objective for a Codex thread, so work can continue across multiple turns toward a defined result.
- Best fit is work that breaks a single prompt: profiling, patching, benchmarking, flaky test reproduction, and audits.
- The leverage comes from clear end conditions. Vague goals turn into extra turns without better output.
Source: news.hada.io/topic?id=29639Read original →
FIG-8301:1
50radar
FIG-8301:1

Mon, May 183 dispatches

#0829
#0829Agents & tools GeekNews2 weeks ago
`Semble`, code search for agents using 98% fewer tokens than grep
70radar
SembleCode search library — returns relevant chunks to cut tokens
Agents get only the relevant code chunks instead of reading whole files. If the latency claim holds in real repos, this is worth testing for repo-aware coding workflows.
- Semble accepts natural-language and code queries, then returns only the snippets likely needed by the agent.
- The headline claim is 98% fewer tokens than grep plus file reads, directly cutting context spend.
- Average repository indexing/search is listed around 250ms, so it fits interactive agent loops if accurate.
- Best use case: wiring it into custom agents or CLI flows where rg finds too much and full-file reads waste context.
Source: news.hada.io/topic?id=29626Read original →
FIG-8291:1
70radar
FIG-8291:1
#0828
#0828Agents & tools GeekNews2 weeks ago
`GemmaCI`: Free PR Reviews via GitHub Actions and `Gemma`
40radar
GemmaCIOpen-source PR reviewer — runs Gemma in GitHub Actions
AI review runs inside GitHub Actions with Gemma. It targets private repos where hosted PR reviewers move to paid plans.
- GemmaCI is open source, so the review workflow can live in the repo instead of a paid SaaS seat.
- The stated replacement target is CodeRabbit; the pain is private-repo PR review cost, not code quality benchmarking.
- No usage numbers or review-quality metrics yet. Treat it as a cost-saving experiment, not a proven reviewer.
Source: news.hada.io/topic?id=29618Read original →
FIG-8281:1
40radar
FIG-8281:1
#0827
#0827Agents & tools GeekNews2 weeks ago
`dev3000`: unified web app debugging timeline capture for AI agents
70radar
dev3000Web debugging CLI — unifies logs, console, and screenshots
Server logs, console output, network calls, screenshots, and user actions land in one timestamped trace. It gives coding agents better bug context than pasted logs.
- Captures dev server logs, browser console, network requests, screenshots, and interactions into one timestamped log.
- Uses Chrome DevTools Protocol to monitor the browser, so it fits normal web app debugging flows.
- Stores captured data under ~/.d3k/{project...}, making traces reusable across prompts and later investigations.
Source: news.hada.io/topic?id=29607Read original →
FIG-8271:1
70radar
FIG-8271:1

Sun, May 172 dispatches

#0826
#0826Agents & tools GeekNews2 weeks ago
`glowed`: Terminal Markdown Browser/Editor for `Ghostty`
40radar
glowedTerminal Markdown TUI — search and edit inside Ghostty
Keeps project docs searchable, previewable, and editable inside the terminal. The useful angle is the handoff from .md notes to an LLM CLI, worth trying if docs already live in-repo.
- glowed targets Ghostty and works as a TUI for finding, previewing, and editing Markdown files inside a project.
- The workflow is terminal-first knowledge management: inspect .md files without opening an IDE or separate notes app.
- LLM CLI handoff is the practical hook. Existing specs, notes, and prompts can become local context faster.
Source: news.hada.io/topic?id=29592Read original →
FIG-8261:1
40radar
FIG-8261:1
#0825
#0825Agents & tools GeekNews2 weeks ago
`Zerostack`: Unix-inspired coding agent written in pure Rust
50radar
ZerostackRust coding agent — minimal stack at roughly 7k LoC
A tiny agent stack with file ops, gated Bash, MCP, and multiple LLM providers. Worth watching if you want inspectable agent plumbing, not a daily-driver replacement yet.
- Written in Rust at roughly 7k LoC; small enough to audit or fork for custom agent experiments.
- Supports multiple LLM providers plus custom providers, so it is not locked to one model API.
- Tool surface covers file read/write/edit, grep, find, directory listing, permission-gated Bash, MCP, and Exa web tools.
Source: news.hada.io/topic?id=29584Read original →
FIG-8251:1
50radar
FIG-8251:1

`agentmemory`, Persistent Memory for AI Coding Agents

`Herdr`, a tmux-style terminal workspace for AI agents

GitHub confirms 3,800 repositories compromised via malicious `VS Code` extension

Google Cloud revamps agent development with `Antigravity 2.0`

`Gemini CLI` will stop working on June 18, 2026

`Codex Relay` Adds Mobile Terminal, Browser, Git, File Viewer, and Markdown for Codex

GitHub Internal Repos Accessed After Employee Device Compromise

`Cursor Composer 2.5` becomes Cursor's most-selected model, with **10x** usage bonus

`Mirage`, a unified virtual filesystem for AI agents

`Goal Setter`, an agent skill for writing safer `Codex` goals

Anthropic Acquires `Stainless` to Expand Agent Tooling

`Project Glasswing`: What `Mythos` Demonstrated

Using Git `--author` to Block AI Bot Spam in GitHub Repos

Using `Codex` `Goals` for Long-Running Tasks

`Semble`, code search for agents using 98% fewer tokens than grep

`GemmaCI`: Free PR Reviews via GitHub Actions and `Gemma`

`dev3000`: unified web app debugging timeline capture for AI agents

`glowed`: Terminal Markdown Browser/Editor for `Ghostty`

`Zerostack`: Unix-inspired coding agent written in pure Rust

`Cursor Composer 2.5` becomes Cursor's most-selected model, with 10x usage bonus