RepoJournal
Anthropic

@anthropics

Claude SDKs and developer tooling

Keep up with Anthropic in about 3 minutes a day: what actually shipped — the commits, pull requests, releases, and security advisories that matter.

One email a day. Unsubscribe in one click.

Pick a date

  1. Fri 19 jun
  2. Sat 27 jun
  3. Sun 28 jun
  4. Mon 29 jun
  5. Tue 30 jun
  6. Wed 1 jul
  7. Thu 2 jul
  8. Fri 3 jul
  9. Sat 4 jul
  10. Sun 5 jul
  11. Mon 6 jul
  12. Tue 7 jul
  13. Wed 8 jul
  14. Thu 9 jul
  15. Fri 10 jul
  16. Sat 11 jul
  17. Sun 12 jul
  18. Mon 13 jul
  19. Tue 14 jul
  20. Wed 15 jul
  21. Thu 16 jul
  22. Fri 17 jul
  23. Sat 18 jul
  24. Sun 19 jul
  25. Mon 20 jul
  26. Tue 21 jul
  27. Wed 22 jul
  28. Thu 23 jul
  29. Fri 24 jul
  30. Today 25 jul
Topics: AI / ML Full archive →

The Wire · Showcase

PLUGIN MARKETPLACE CLEANUP COMPLETE; CONNECT-RUST CUTS CLIENT STREAMING MEMORY TO ZERO

By RepoJournal · Filed · About Anthropic

iainmcgin qing-ant
2 people shipped this
iainmcgin @iainmcgin 2 cited qing-ant @qing-ant 1 cited

Anthropics standardized plugin validation across the marketplace while gutting the memory footprint of streaming RPC clients — both ship today.

The claude-plugins-official repo completed a sweeping marketplace audit, replacing hand-rolled validators with the shared validate-plugins action suite and pinning all 62 external plugin SHAs to their current upstream HEAD [1]. This means broken marketplace entries like the nonexistent autofix-bot [5] and dormant plugins (flint [2], optibot [3], versori-skills [4]) are now caught automatically. Connect-rust shipped the bigger win: call_client_stream now streams request bodies through a 32-depth mpsc channel instead of buffering entire payloads in memory before the wire ever sees a byte [6] [8]. Peak memory went from O(total payload) to O(single envelope). The same release lands a TLS-aware axum serve helper that stamps peer certs into request extensions, making handler code portable between standalone Server and axum apps [7]. Buffa-codegen fixed two clippy lints exposed by the v0.5.0 per-proto split layout: Self:: qualification in oneof serde [9] [11] and unused_qualifications in cross-proto references [10] [12]. Claude Agent SDK Python v0.1.77 shipped actionable error messages — when the CLI exits with error results like error_max_turns, consumers now get the actual error text instead of a generic 'Command failed with exit code 1' [13] [14] [15].

One email a day. Unsubscribe in one click.

Action items

References

  1. [1] Adopt validate-plugins action suite; pin all external SHAs (#1762) anthropics/claude-plugins-official
  2. [2] Remove flint from marketplace (#1769) anthropics/claude-plugins-official
  3. [3] Remove optibot from marketplace (#1768) anthropics/claude-plugins-official
  4. [4] Remove versori-skills from marketplace (#1765) anthropics/claude-plugins-official
  5. [5] Remove broken autofix-bot marketplace entry (#1047) anthropics/claude-plugins-official
  6. [6] client: stream call_client_stream request body via channel ↗ anthropics/connect-rust
  7. [7] axum: serve_tls helper + mtls-identity example ↗ anthropics/connect-rust
  8. [8] client: stream call_client_stream request body via channel (#84) anthropics/connect-rust
  9. [9] fix(buffa-codegen): use Self:: in oneof serde + inlined format args in enum serde ↗ anthropics/buffa
  10. [10] fix(buffa-codegen): add unused_qualifications to ALLOW_LINTS ↗ anthropics/buffa
  11. [11] fix(buffa-codegen): use Self:: in oneof serde + inlined format args in enum serde (#104) anthropics/buffa
  12. [12] fix(buffa-codegen): add unused_qualifications to ALLOW_LINTS (#102) anthropics/buffa
  13. [13] fix(query): surface result error text in trailing ProcessError instead of generic exit code ↗ anthropics/claude-agent-sdk-python
  14. [14] fix(query): suppress redundant ProcessError after error result (#918) anthropics/claude-agent-sdk-python
  15. [15] v0.1.77 ↗ anthropics/claude-agent-sdk-python

Quick answers

What shipped in Anthropic on May 8, 2026?
Anthropics standardized plugin validation across the marketplace while gutting the memory footprint of streaming RPC clients — both ship today. In total, 40 commits, 37 pull requests, and 5 releases landed.
Who contributed to Anthropic on May 8, 2026?
2 developers shipped this update, including iainmcgin and qing-ant.
What were the notable Anthropic updates?
Adopt validate-plugins action suite; pin all external SHAs (#1762), Remove flint from marketplace (#1769), and Remove optibot from marketplace (#1768).

More from @anthropics

Anthropic @anthropics

CLAUDE AGENT SDK FIXES STDIN CLOSURE BUG IN BACKGROUND TASKS

The Python SDK's query method was prematurely closing stdin when background subagents were still in flight, breaking tool calls and silently bypassing hooks - now fixed in v0.2.127.

github-actions[bot] GitHub Actions ashwin-ant
ai 16 shipped 1-min read
Anthropic @anthropics

BUFFA v0.9.1 PATCHES REGRESSION THAT BROKE ORDINARY SCHEMAS

Buffa shipped an emergency patch overnight after v0.9.0 broke codegen on schemas with a few hundred proto files, small enough to hit in production.

iainmcgin github-actions[bot] Bryan Thompson github-actions +1
ai 113 shipped 1-min read
Anthropic @anthropics

CLAUDE FOUNDATION MODELS ADDS APP ATTEST, PLUGIN ECOSYSTEM STABILIZES

iOS developers can now ship Claude calls without API keys in the binary, backed by Apple's Secure Enclave.

Bryan Thompson markpikemarkpike github-actions mmoore +1
ai 111 shipped 1-min read
Anthropic @anthropics

BUFFA FIXES V0.9.0 REGRESSION, CLAUDE PLUGINS ECOSYSTEM GAINS 9 NEW INTEGRATIONS

Buffa's codegen was silently rejecting moderately large schemas due to a memory bound meant only for untrusted input, but a fix shipped overnight restores throughput and clears the path for googleapis-scale proto sets.

Bryan Thompson iainmcgin ogarciarevett fallintoplace +2
ai 156 shipped 2-min read

Daily updates, in your inbox

Follow Anthropic

Keep up with Anthropic in about 3 minutes a day: what actually shipped — the commits, pull requests, releases, and security advisories that matter.

or

One email a day. Unsubscribe in one click. Read a past issue →

Elsewhere on the wire

AI Agents AI Agents

CLAUDE OPUS 5 LANDS ACROSS THE STACK

The newest Anthropic model is now live in langchain, Cline, and llama-index, with native support for extended reasoning and 1M context windows.

github-actions[bot] hntrl dependabot ak684 +6
ai-agents 28 shipped 1-min read
Local LLMs Local LLMs

OLLAMA LANDS LAGUNA SUPPORT AND CRUSHES MEMORY LEAKS WHILE SGLANG HITS V0.5.16 WITH CONFIDENCE-DRIVEN SPECULATIVE DECODING

Ollama shipped three critical performance and reliability fixes for Metal residency and concurrent access patterns, while SGL-Lang released 0.5.16 with a new speculative algorithm hitting 383.7 tok/s on DeepSeek-V4.

dhiltgen ParthSareen Xuan-Son Nguyen Johannes Gäßler +11
llms 210 shipped 2-min read
CachyOS @CachyOS

HYPRLAND V0.56 FIXES LAND, PACKAGE ECOSYSTEM ROLLS FORWARD

Hyprland configuration updated for v0.56 compatibility across multiple desks, while the AUR-derived ecosystem locked in four automated package bumps.

cantosun99 Jinra Aarrayy Valeri +7
infra 85 shipped 1-min read
Elixir & Phoenix Elixir & Phoenix

LIVEVIEW ASYNC CLEANUP FIX SHIPS ALONGSIDE RANGE OPTIMIZATIONS

Phoenix LiveView closes a critical async task test failure while Elixir cuts unnecessary abs calls from Range operations.

Barna Kovacs Alexander Gubarev SteffenDE José Valim +1
elixir 19 shipped 1-min read
Want every project, not just this one?