Agent DailyAgent Daily
Previous

Daily Roundup

Wednesday, March 18, 2026

Next
44 articles3 sources

Top Story

GitHubintermediate

[Release] anthropics/claude-code v2.1.78: v2.1.78

ashwin-antMar 18, 2026

Claude Code v2.1.78 introduces enhanced plugin state persistence, improved terminal notifications in tmux environments, and streaming response text. The release fixes critical issues including sandbox security vulnerabilities, API error handling loops, permission rule enforcement, and various UI/UX problems across VS Code, terminal modes, and voice functionality.

  • New `StopFailure` hook event fires when turns end due to API errors (rate limits, auth failures)
  • Plugin persistent state via `${CLAUDE_PLUGIN_DATA}` survives updates; uninstall prompts before deletion
  • Added `effort`, `maxTurns`, and `disallowedTools` frontmatter support for plugin-shipped agents
  • +7 more key points...
MCP ServersDeploymentTool UseSecurityUpdates & News
Read full article →

By Topic

Agent Teams

See all 24

Memory Systems

See all 4
GH

[Release] openai/openai-agents-python v0.12.4: v0.12.4

OpenAI Agents Python v0.12.4 release includes critical bug fixes for MCP (Model Context Protocol) tool invocations, retry logic improvements, and SQLite session memory handling. The update normalizes cancelled MCP invocations into tool errors, adds resilience for transient HTTP failures, fixes custom table name support in AdvancedSQLiteSession, and caps jittered retry delays. Documentation improvements and CI hardening were also included.

seratch

63%
YT

Getting started with projects in Claude.ai

This tutorial introduces Projects in Claude.ai, a feature that enables users to organize their work by maintaining persistent context and custom instructions across conversations. Projects allow you to group related conversations, documents, and settings in one place, making it easier to manage complex workflows and maintain consistency across multiple interactions with Claude.

Anthropic

51%
HN

Ask HN: Burning $100K/week on LLM tokens – what are you doing to cut costs?

A high-volume LLM user spending $103K/week on AI coding agents shares cost-reduction strategies and seeks battle-tested approaches. Current tactics include prompt caching (~30% savings), model tiering (Haiku for simple tasks, Sonnet for complex), and aggressive history truncation. The user is exploring token compression, intelligent context routing, and self-hosted models as next steps, with infrastructure positioned at an OpenClaw gateway for middleware injection.

seenkitty

48%

Skills & Tools

Updates & News

Tool Use

VPS Hardening

MCP Servers

Integrations

Today's Breakdown

Sources

YouTube37
GitHub5
Hacker News2

Content Types

video (37)release (5)discussion (1)tutorial (1)

Difficulty

beginner
25
intermediate
18
advanced
1

Want to save articles & build playbooks?

Create a free account to save articles to your library, build AI-generated implementation playbooks, and get content matched to your stack.

Or just get it by email

No account needed. Unsubscribe anytime.