free
free, forever
- watch up to 5 sources from 2 platforms
- read the public feed
- install the MCP (rate-limited per IP)
- subscribe to the atom / rss feed
no signup needed. paste one line in your terminal.
ClaudeMon
give your Claude agents Claude awareness.
we watch the ecosystem. you query us. claude knows what's new.
how it works
sources → ClaudeMon → consumers
we watch this
X
GitHub
Hacker News
Anthropic
RSS
claude.ai
we index · dedupe · FTS-search · serve
ClaudeMon
your Claude reads it
Claude Desktop
Claude Code
any MCP client
live feed
connecting… · 30 items-
I used to love Claude, but the latest models are slowly ruining it
12 points · 11 comments · by Brajeshwar
-
v2.1.207
What's changed - Auto mode is now available without opt-in on Bedrock, Vertex AI, and Foundry; disable via in settings - Fixed the terminal freezing and keystrokes lagging while streaming responses containing very long lists, tables, paragraphs, or code blocks - Fixed remote managed settings from a non-interactive run (, the SDK) being permanently recorded as consented without ever showing the security consent dialog - Fixed spurious prompt-injection warnings triggered by benign system-generated conversation updates - Fixed the auto-updater overwriting a custom launcher script or symlink at on every release; now reports an externally managed launcher - Fixed compound commands with prompting for permission when the only output redirect was to - Fixed the transcript jumping above the start of the answer when a response finishes streaming - Fixed being left in the repo's (breaking go-git tools like ) after the last worktree was removed - Fixed malformed bracket patterns in rules globs, skill paths, , and breaking file reads, file suggestions, and worktree creation - Fixed a crash loop in agent teams where a malformed teammate mailbox message caused repeated errors every second until the mailbox file was manually deleted - Fixed background sessions auto-named by accepting a plan not showing that name on their agent-view row - Fixed background sessions that entered a git worktree resuming blank after a cold reopen from the agent list - Fixed Remote Control task status updates being lost when the connection recovered from a network interruption or credential refresh - Fixed Remote Control sessions hosted by the desktop app not showing background agent and workflow progress on mobile and web - Fixed Deep research runs labeling every Fetch-phase agent "unknown" — chips now show the source hostname - Fixed Bedrock repeatedly requesting fresh AWS SSO credentials from IAM Identity Center on every API request - Improved agent view: pasting the same text again now expands the co
-
v0.3.207
What's changed - Fixed returning without being rejected as a deny with a raw ZodError message; the tool now runs with the original input per the documented contract - The Agent tool's structured result now has a published SDK type () that matches the emitted object exactly Update [code]
-
One Wikipedia page costs your AI agent 68,000 tokens
10 points · 6 comments · by arhamislam5766 — i use claude code daily and measured what pages cost it while doing research. an average wikipedia article, for instance, is 68,240 tokens of raw html (tiktoken); nike's homepage is 353,000.<p>claude code's built-in webfetch handles the easy case well. it summarizes wikipedia to about 950 tokens and clears cloudflare on some sites like indeed and ticketmaster. but, and there's always a but, on js-rendered and some anti-bot pages it returns nothing.<p>quotes.toscrape.com/js gi
-
GPT-5.6, Grok 4.5, Claude, and Muse Spark build the same 4 apps
30 points · 8 comments · by hershyb_
-
sdk: v0.111.0
0.111.0 (2026-07-10) Full Changelog: sdk-v0.110.0...sdk-v0.111.0 Features api: add support for dreaming (77b28a6) tools: gate session tool calls on evaluatedpermission; bound idle by server stopreason (68a6d7b) Chores docs: small updates to field descriptions (e25b885) docs: update model example (a33f3f0) docs: updates to descriptions and examples (eac4bac)
-
Ben Bernanke Joins Anthropic Oversight Trust
17 points · 2 comments · by Jimmc414
-
v2.1.206
What's changed - Added directory path suggestions to , matching behavior - Added a check that proposes trimming checked-in files by cutting content Claude could derive from the codebase - now auto-allows to the repo's configured push remote (, or the sole remote when only one is configured) in addition to - Gateway: now supports Anthropic-operated public gateway endpoints - now asks for confirmation before entering a git worktree outside the project's directory - Background agents now upgrade to a new version in the background right after a Claude Code update, instead of paying a slow stale-session upgrade when you attach - Fixed an expired login failing every model with a misleading "There's an issue with the selected model" error instead of prompting to run - Fixed and not responding to keyboard input on startup - Fixed MCP servers configured via or ignoring a per-server , which caused long-running MCP tool calls to time out at the 60s default in fresh sessions - Fixed being silently ignored by / background workers; the shell-exported override now follows the dispatching session - Fixed OAuth MCP servers requiring manual re-authentication after a single failed token refresh - Fixed pointing at an MCP server crashing with "MCP tool not found" on cold start before the server finishes connecting - Fixed picker rows printing a price for a different model than the row named, and stopped quoting first-party list prices on providers that don't bill them - Fixed server-provided model rows being misplaced in the picker when an entitlement or allowlist restriction drops the row they were positioned against - Fixed desktop sessions getting stuck showing "running" after a slash command was sent mid-turn - Fixed keyboard input being ignored in the agents view when a setup prompt appeared before a bare on Windows - Fixed leaving the removed job in the daemon roster, causing the row to reappear in - Fixed showing "Unknown command" when logged out — it now explains how to sign in
-
v0.3.206
What's changed - Added frames to stream-json and SDK sessions, reporting each uuid-stamped message's terminal state (////); zero-API results no longer report stale Update [code]
-
Show HN: I built a web tool to see and edit what an AI thinks before it answers
12 points · 2 comments · by ada1981 — I run a small AI lab and playground and got super excited about Anthropics paper "Verbalizable Representations Form a Global Workspace in Language Models" (<a href="https://transformer-circuits.pub/2026/workspace/index.html" rel="nofollow">https://transformer-circuits.pub/2026/workspace/index.html</a>)<p>It talks about how they use a tool they call a Jacobian Lens to view inside the middle layers of LLM while it's working before it
-
Show HN: Devthropology – Better Insights for GitHub Repos
26 points · 9 comments · by dpc94 — Devthropology is a passion project built on top of GitHub pull data. The name is a play on developer anthropology. Pull request data can be cut a lot of ways. The functionality has been built out of curiosity as I want to see different insights into codebases that I work on. Some of the data is typical and other parts I haven't seen elsewhere.<p>I think of this as an improved GitHub Insights page, with faster performance, more detail, and a focus on how work moves through a codebase. The ma
-
Show HN: Policy enforcement for Claude Code, Cursor, and Codex
10 points · 1 comments · by carlosjimenez1 — Show HN: Runtime authorization for Claude Code, Cursor, and Codex<p>Hi HN, Fernando and I built Kastra. Kastra intercepts AI agent tool calls and evaluates them against deterministic policies before they execute. This is aimed at developers using coding agents like Claude Code, Codex, Cursor, and OpenClaw.<p>We built Kastra after one of our Cursor agents almost executed DELETE FROM customers WHERE status='test' against a production database. We caught it before it ran, but it made us r
-
A new way to reflect on how you use Claude
41 points · 53 comments · by surprisetalk
-
Show HN: Getting GLM 5.2 running on my slow computer
141 points · 27 comments · by vforno — A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me.<p>But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this poss
-
v0.3.205
What's changed - Interrupt control responses now include (UUIDs of queued async messages that will still run), returns the typed receipt, and advertises an capability for feature detection - Added structured and fields to peer-message session events, exposing the sender display name and decoded message body Update [code]
-
v2.1.205
What's changed - Added an auto mode rule that blocks tampering with session transcript files - Fixed silently producing unstructured output when the schema was invalid, and schemas using the keyword being rejected - Fixed a message sent while Claude was working being silently lost when the turn ended at the limit - Fixed Windows worktree removal deleting files outside the worktree when an NTFS junction or directory symlink existed inside it - Fixed background agents staying shown as "failed" or "completed" in the agent list after being resumed with - Fixed background jobs flipping from "needs input" back to "working" in the agent list when the agent's turn contained no readable text - Fixed erroring when a background agent was mid-upgrade restart instead of waiting for it to come back - Fixed session-to-PR linking missing a PR created in a Bash call whose output exceeded the 30K inline limit - Fixed getting stuck when a server name contains unsupported characters; invalid names are now reported and remaining servers still import - Fixed a plugin LSP server that fails to initialize preventing a valid LSP server from another plugin handling the same file extension - Fixed a Windows crash when the directory Claude was launched from is deleted, locked, or unmounted while a command is running - Fixed a crash when a file watcher was closed while a directory scan was still in flight - Fixed project verify skills being rewritten on every session instead of only when a documented command changed - Fixed the agent view rendering one line too high and clipping its header when the job list slightly overflowed the screen - Fixed background tasks in the web and mobile Remote Control panels showing stale "Running" status by forwarding full task state on every membership change - Improved auto mode to ask before running on a variable it can't resolve from context - Auto-update binary downloads now stream to disk instead of buffering in memory, cutting the updater's peak memory usag
-
The classifiers Anthropic puts in front of Fable are too zealous
213 points · 189 comments · by karrot-kake
-
Maybe Anthropic and OpenAI Are Not the Future of Artificial Intelligence
14 points · 4 comments · by littlexsparkee
-
Ask HN: Another "Hacker News" with less AI and more human-focused hacking news?
86 points · 53 comments · by weird_trousers — I am done with articles stating "I used this LLM to do that", or "Look, this agent did that in 2 minutes!". I want content more user-centric, less openai / anthropic, and more "human-in-the-loop" articles.<p>Any other website to recommend? I think lobste.rs was a good hacker news aggregator, but I don't know if it is still relevant today...<p>UPDATE:<p>Some recommendations, provided by the answers:<p>- https://hackaday.com/ - https:/&
-
Show HN: Abralo – Free, easy way to run several Claude Code agents in one window
17 points · 11 comments · by cwbuilds — Hi guys,<p>I've been using Claude Code for almost everything lately. Have given one an email account so it can research business leads, draft emails, fact-check them and clear them with me before sending (works really well by the way). I also tend to have a few Claude Code agents running at any one time for coding.<p>I used to create a split terminal to manage them from there, but found working in the terminal all day pretty depressing and, more importantly, found it hard to follow Claude C
-
Show HN: Abralo – Free, easy way to run several Claude Code agents in one window
17 points · 11 comments · by cwbuilds — Hi guys,<p>I've been using Claude Code for almost everything lately. Have given one an email account so it can research business leads, draft emails, fact-check them and clear them with me before sending (works really well by the way). I also tend to have a few Claude Code agents running at any one time for coding.<p>I used to create a split terminal to manage them from there, but found working in the terminal all day pretty depressing and, more importantly, found it hard to follow Claude C
-
Geosql: A Claude/Codex skill for geospatial data
10 points · 0 comments · by rzk
-
v2.1.204
What's changed - Fixed hook events not streaming during SessionStart hooks in headless sessions, which could cause remote workers to be idle-reaped mid-hook
-
v0.3.204
What's changed - Updated to parity with Claude Code v2.1.204 Update [code]
-
v2.1.203
What's changed - Added a warning when your login is about to expire, so you can re-authenticate before background sessions are interrupted - Added a grey ⏸ badge to the footer when in manual permission mode, making the active mode always visible - Added the session's additional working directories to MCP , with sent when the set changes - Fixed opening or switching background agent sessions on macOS stalling for 15–20 seconds due to a false low-memory detection (regression in 2.1.196) - Fixed background sessions becoming permanently unresponsive to attach, replies, and stop when the daemon's session token went stale — the session now recovers automatically - Fixed returning to silently stopping running subagents and re-running the prompt from scratch — their work now carries over - Fixed a memory and per-turn CPU regression in interactive sessions: the context-usage indicator no longer re-analyzes the entire transcript after every turn - Fixed background agents inheriting a stale from the daemon instead of the dispatching shell, causing missing tools on Windows - Fixed background and agent-view sessions dropping a shell-exported , which sent API keys to the default endpoint and failed with 401 - Fixed Bash failing with "argument list too long" in repos with many git worktrees - Fixed worktree-isolated subagents sometimes running shell commands in the parent checkout instead of their own worktree - Fixed worktree creation rejecting nested repositories in multi-repo workspaces, leaving background sessions unable to isolate and edit - Fixed background agents crash-looping when their working directory was deleted, replaced by a file, or became an invalid path — they now fail once with a clear error - Fixed a background daemon auto-upgrade failure silently killing all running background sessions - Fixed and failing to find background agents spawned by another agent — errors now list running agents by id and description - Fixed the composer discarding your typed message w
-
v0.3.203
What's changed - Added a system message with the full set of live background tasks on every membership change, so consumers can track background activity as a level instead of pairing / edges - Fixed stable releases shipping a with unresolved type references that broke consumer typechecking with disabled Update [code]
-
Abnormal.ai Response to Anthropic Lawsuit
10 points · 2 comments · by babelfish
-
Anthropic is launching Claude Cowork on mobile and web
10 points · 0 comments · by ilreb
-
Show HN: Rowboat – Open-source, local-first alternative to Claude Desktop
12 points · 2 comments · by segmenta — Claude’s desktop app is brilliant, but for our own daily work we kept wanting it to be less like a chat app and more like a full-fledged work app. Rowboat is our attempt at that, including the ability to build your own work surfaces inside Rowboat (more below).<p>Our repo is <a href="https://github.com/rowboatlabs/rowboat" rel="nofollow">https://github.com/rowboatlabs/rowboat</a>, and there’s a demo video here: <a href="https://www.youtube.com&#x
-
Show HN: Rowboat – Open-source, local-first alternative to Claude Desktop
12 points · 2 comments · by segmenta — Claude’s desktop app is brilliant, but for our own daily work we kept wanting it to be less like a chat app and more like a full-fledged work app. Rowboat is our attempt at that, including the ability to build your own work surfaces inside Rowboat (more below).<p>Our repo is <a href="https://github.com/rowboatlabs/rowboat" rel="nofollow">https://github.com/rowboatlabs/rowboat</a>, and there’s a demo video here: <a href="https://www.youtube.com&#x
pricing
free for everyone. paid if you want it piped in.
reading the public feed is free forever. paid covers the power-user surface — your own sources, your own API key, your own Obsidian vault.
pro
launch pricing locks soon
- unlimited sources · unlimited platforms
- obsidian export — markdown bundle of your watchlist
- personal API key with elevated rate limits
- codex MCP integration when it lands
drop your email. we'll tell you when pricing locks.
setup
three clients, one URL. paste & go.
claude desktop
settings → connectors → + → paste the URL
claude code
one line in your terminal
codex (coming soon)
codex MCP variant is on the v1.1 roadmap.
the bridge
claude doesn't know it got better an hour ago. ClaudeMon fills that gap.