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-
v0.3.265
What's changed - Added and to a synthetic turn's first reply and result for a message sent with and a , naming the message that started it - Added and to the first reply and the result of a turn Claude Code started itself, such as a resume, naming the messages you sent that it picked up mid-turn - Fixed missing from the success result of a turn that sent no API request, such as a slash command - Fixed multi-turn sessions resetting the shell working directory to the option at each new user message; a made by the agent now persists across turns, as in the interactive app - Changed to be set on the first reply after each change of the message a turn is answering, instead of on one reply frame per turn - Updated to parity with Claude Code v2.1.265 Update [code]
-
v2.1.265
What's changed - Added and to the telemetry Claude Desktop and Cowork send through a Claude apps gateway, matching terminal sessions - Added support for pointing at a folder of plugins: each child folder with a manifest loads, and children added or removed while running are picked up - Added a 1 GB cap on tool results saved to disk; the in-conversation preview says when a saved file was truncated - Fixed resuming a foreground-spawned subagent changing its tool list and system prompt prefix, which broke prompt-cache reuse for that agent - Fixed agent teammates and resumed subagents moving SubagentStart hook context and preloaded skills out of the prompt prefix on later turns, which broke prompt-cache reuse - Fixed resume after the previous process died while a tool was running: the last prompt is no longer rewritten, and the interrupted tool call is kept and marked interrupted - Fixed being rejected with "Model not found" - Fixed syntax-highlighted code in permission prompts and messages sometimes omitting a character after a Ruby , Erlang , or Perl sigil - Fixed the fullscreen transcript jumping by one row whenever the slash-command or @-file suggestion list opened or closed - Fixed a plugin path containing a backslash bypassing the symlink containment check on macOS and Linux - Fixed plugin directories whose names begin with two dots being wrongly refused as outside the plugin root - Fixed VS Code and SDK sessions occasionally requiring re-login when a session was closed while refreshing its token - Fixed Remote Control sessions sending the end-of-turn signal before the reply's last message, which could show a reply as finished in the Claude app before its last part arrived - Fixed background () sessions occasionally being retired mid-turn when a message arrived just before the idle timeout - Fixed Claude Code's own git status and diff probes running clean filters configured by a nested repository inside the working tree - Fixed the advisor tool and its instruction
-
AI Giants Work Hand-in-Hand with The Pentagon, Contracts Reveal
10 points · 4 comments · by sea-gold
-
The VMs Powering Mobile Agents (Instinct, Claude Code)
12 points · 1 comments · by RohanAdwankar
-
Denzel Explains AI "Slop"
10 points · 0 comments · by freakynit
-
Coop – Isolated VM Environments for Running Claude Code and Codex
10 points · 2 comments · by aggrrrh
-
v0.3.263
What's changed - Updated to parity with Claude Code v2.1.263 Update [code]
-
v2.1.263
What's changed - Bug fixes and reliability improvements
-
Poetry book that Anthropic tried to censor
15 points · 4 comments · by cainxinth
-
Anthropic & friends caught paying religious NGO's 3.3M for propaganda
10 points · 5 comments · by nullbio
-
Show HN: Moadim.io – A scheduler for agents
14 points · 7 comments · by tupe12334 — Why can't we get an agent scheduler that supports all of the following:<p>- git compatible<p>- agent agnostic<p>- 100% open source<p>- os and system-agnostic<p>- multi-runner support<p>- support mcp/ui/http<p>- unlimited routines/crons<p>So I built one, moadim.io is a local Rust daemon you install in the target machine, give it a name and manage its routines via a Git repository, wants a new routine that send you a daily message from this machine? Create a pr and merge, have
-
Portal by Spotify cut my Claude Code token usage by 90%
43 points · 14 comments · by cebert
-
Claude Code skills for advanced context engineering techniques and patterns
11 points · 0 comments · by leovs09
-
aws-sdk: v0.7.0
0.7.0 (2026-09-04) Full Changelog: aws-sdk-v0.6.6...aws-sdk-v0.7.0 Features api: add support for sending a workspace ID on more endpoints (a11e6f1)
-
foundry-sdk: v0.4.5
0.4.5 (2026-09-04) Full Changelog: foundry-sdk-v0.4.4...foundry-sdk-v0.4.5 Chores examples: refresh platform model IDs (376) (2637d11)
-
bedrock-sdk: v0.33.4
0.33.4 (2026-09-04) Full Changelog: bedrock-sdk-v0.33.3...bedrock-sdk-v0.33.4 Chores examples: refresh platform model IDs (376) (2637d11)
-
vertex-sdk: v0.19.7
0.19.7 (2026-09-04) Full Changelog: vertex-sdk-v0.19.6...vertex-sdk-v0.19.7 Chores examples: refresh platform model IDs (376) (2637d11)
-
sdk: v0.124.0
0.124.0 (2026-09-04) Full Changelog: sdk-v0.123.0...sdk-v0.124.0 Features api: add Claude Tag category and user breakdowns to usage reports (669ff22) api: add named types for organization compliance settings state (54be8da) api: add support for sending a workspace ID on more endpoints (a11e6f1) Bug Fixes repair custom-code merge in messages resources (455) (7ac43b9) tools: create agent-toolset files and directories owner-only (485) (a9c2298) Chores internal: bundle the mock server spec and update breaking-change detection (8752d02) internal: codegen related update (a63afbc) tests: reword the skip reason on the path-level query param tests (999bee5) Documentation api: update a few doc strings (2ef3d59)
-
v1.4.0
1.4.0 (2026-09-04) Full Changelog: v1.3.0...v1.4.0 Features api: add Claude Tag category and user breakdowns to usage reports (9fce1e4) api: add named types for organization compliance settings state (1de1957) api: add support for sending a workspace ID on more endpoints (d1d2c01) Bug Fixes client: raise a clear error when an httpx object is passed instead of an httpx2 one (9447099) repair custom-code merge in messages resources (580) (85454ca) Chores examples: refresh platform model IDs (499) (182abb5) internal: bundle the mock server spec and update dev tooling (f9b0cf2) internal: clean up code comments (578) (d202327) internal: fix mypy unreachable error in detect-breaking-changes script (07834f6) internal: narrower codeowners scope (daca8f1) internal: revert codeowners change (41aa767) tests: remove stale warning filters (ba9bf35) tests: reword the skip reason on the path-level query param tests (6b5046a) Documentation api: update a few doc strings (26c509d)
-
Fermat's Last Theorem: Anthropic has beaten me to it
22 points · 2 comments · by ravenical
-
v0.3.261
What's changed - Added to send over stdin so the launch command line no longer grows with the plugin count (fixes Windows start failures with many plugins) - Fixed throwing "Object not disposable" in runtimes without a native , such as Node ≤22 contexts (Jest's environment, vitest /) and Node <18.18 - Updated to parity with Claude Code v2.1.261 Update [code]
-
v2.1.261
What's changed - Added an "Organization policy" line to and that says why your organization's policy could not be loaded, such as a proxy not passing the endpoint through - Added and settings to raise how much command and background-task output Claude receives inline before it is saved to a file, up to 128K characters - Added to read the subagent system prompt from a file, for prompts too large to pass on the command line - Added to show which loaded skills go unused and what they cost in context, so you can prune them - Fixed typed or pasted characters occasionally landing out of order or being dropped during fast input or key repeat - Fixed printing a false "couldn't be resolved" error when the working directory is on a automount - Fixed the Bedrock setup wizard hanging when AWS or an AWS credential helper never responds (it now times out with a clear error), and its model checks failing behind a TLS-inspecting proxy - Fixed cloud sessions discarding a plugin synced from claude.ai when managed settings force-enable it in , then falling back to a marketplace clone that could fail - Fixed being unable to delete the character immediately before an inline chip in the prompt input - Fixed resuming a session losing hook output and other context around parallel tool calls, which changed the resumed request - Fixed Remote Control showing a stale permission mode when a phone, browser, or claude.ai app attaches to a terminal session or after the mode changes in the terminal - Fixed Remote Control sessions showing as still working (stuck spinner and Stop button) after stopping a turn from a connected phone or browser, or after a local slash command like - Fixed SDK and cloud sessions ignoring a Stop or interrupt sent just after the first prompt, before the turn had started; the turn now stops instead of running to completion - Fixed Remote Control uploading a session pulled with into the connected session, which appeared appended to the original on phone and web - Fixed Remo
-
Fermat's Last Theorem in Lean 4
11 points · 3 comments · by aaraujo002
-
Formalizing Fermat's Last Theorem
37 points · 4 comments · by jlebar
-
Show HN: Jigsaw Haiku
62 points · 20 comments · by windowshopping — Hi HN! Jigsaw Haiku was originally designed with my puzzles site The Daily Baffle (<a href="https://dailybaffle.com" rel="nofollow">https://dailybaffle.com</a>) in mind. But once I had built it, I realized it just didn't quite fit with the aesthetic of the Baffle's other puzzles, so I decided to put it up separately.<p>While most of the puzzles on the Daily Baffle were intended to be rather challenging, for this one I really just wanted to make something somewhat be
-
Nobody Is Saying Why OpenAI and Anthropic Had Outages
21 points · 1 comments · by jslakro
-
Corporate America Is Getting Hooked on Open-Source A.I
11 points · 2 comments · by aaraujo002
-
v0.3.260
What's changed - Added optional to system messages, linking thinking progress to the user message that triggered the turn - Added optional , , and fields to the success result message for remote-session latency breakdowns - Fixed (either spelling) being dropped by the restrictive-only filter instead of turning auto mode off for the spawned session - Fixed reporting success when no files could be restored (for example when checkpoint backups are missing); it now fails - Changed results to append the last StructuredOutput tool error; validation errors now name the offending key, allowed values, and actual length or count - Changed to also re-emit during an exceeded window on repeat 429s (about once per 30 seconds per limit window), so stream consumers can refresh stale rate-limit state - Updated to parity with Claude Code v2.1.260 Update [code]
-
v2.1.260
What's changed - Added a diff panel that opens beside the conversation in fullscreen mode and shows your uncommitted changes as Claude edits; toggle it with - Added a likely cause for prompt-cache misses (e.g. tool definitions or system prompt changed, idle past the TTL) to and the status line's field - Added to headless sessions, so it appears in the Claude Code Desktop and SDK command lists - Added a text form of (, , ) for the desktop app, Remote Control, and other headless (/Agent SDK) sessions - Added to the Claude apps gateway for IdPs that return an idtoken on refresh only when asked for again - Added Claude apps gateway support for newer Claude Desktop keys in policy blocks, including and - Fixed // permission rules whose path contains parentheses being dropped as invalid or ignored by the Bash sandbox, which left "read-only" folders writable - Fixed one file permission rule with an uncompilable pattern (e.g. an unclosed ) making every file edit fail with ; such a deny rule now guards the literal path it spells - Fixed Bash permission checks auto-approving zsh commands that hide a command substitution in a REPORTTIME, REPORTMEMORY or DIRSTACKSIZE assignment; these now prompt for approval - Fixed Bedrock model discovery, token counting and AWS SSO/STS credential calls failing with "unable to get local issuer certificate" when the corporate root CA is only in the OS certificate store - Fixed on macOS hiding the user's git config from sandboxed git and hiding a worktree-isolated sub-agent's own checkout - Fixed managed settings not loading for claude.ai Enterprise/Team users who also had a leftover API key from an earlier - Fixed listing a signed-in claude.ai account and a configured API key as if both were in effect; the credential not in use is now marked - Fixed managed entries keyed on a bundled skill's alias (e.g. for ) not applying, and deny rules not covering a nested skill listed as - Fixed agents ignoring the tag on an pin and silently running with a 2
-
Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out
14 points · 1 comments · by screm
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.