AI Agent News: Releases, Launches and Usage Jumps, Live · page 14
-
Zed 1.27.0 released
Improved Agent Panel memory usage by loading tool-call diffs and parsing thread message Markdown only when first viewed, instead of when loading a thread. (#65444, #65470; thanks Vanuan); Improved AI commit message generation by using the three most recent…
-
Kimi K3.1 Pro now has more ZDR providers on AI Gateway
Kimi K3.1 Pro models are now available through multiple Zero Data Retention providers on Vercel's AI Gateway, expanding beyond Moonshot AI.
-
E2B 2.63.0 released
a8155c4: Add strict to pause() (default false). With strict: true / strict=True a pause is refused with ServiceBusyError / ServiceBusyException while the sandbox's guest agent does not respond… (+2 more releases that day)
-
Four layers of context engineering for production AI agents: How Deep Insight applies them in working code
AWS post describes a four-layer context engineering framework for production AI agents, implemented in Deep Insight, an open source multi-agent data analysis solution using Strands Agents SDK and Amazon Bedrock.
-
How Indegene is modernizing and scaling enterprise data quality in life sciences
Indegene built an LLM-powered Data Quality Agent on AWS that generates context-aware data quality rules and produces SQL and Python code under human-in-the-loop governance for life sciences organizations.
-
How U Mobile built agentic telco operations with Amazon Bedrock AgentCore
U Mobile deployed AiDaH, an agentic operations platform on Amazon Bedrock AgentCore, handling over 150 operational scenarios and reducing trouble tickets by up to 84.5% nine months after launch.
-
See the agents, set the terms: New visibility and control for personal agents
Cloudflare announced tools for site owners to see and control personal AI agent access to their websites.
-
Mastra 1.82.0 released
@mastra/temporal@0.5.0: Steps now validate inputSchema and requestContextSchema before running (can fail runs that previously “succeeded” with wrong input); set validateInputs: false to opt out.; Experimental memory changes: experimental_subconscious and…
-
Langfuse 4.75.0 released
feat(ai-gateway): raise Pro/Team/Enterprise gateway limits to 10k req/min and 5 GiB/min; feat: improve internal error messages; feat(skills): trace Codex skill resource loads
-
Dify 1.19.0 released
Follow the hierarchy. Expand called Workflow Tools to see their internal execution steps under the invoking Tool span.; Understand each invocation. Repeated calls and failures retain their place in the trace.; Keep the LLM context. Inspect formatted prompts…
-
datasette-apps 0.3a0
datasette-apps 0.3a0 improves LLM integration for creating custom HTML applications in Datasette, with app tagging support in chat.
-
DevRev delivers autonomous self-service with GPT-6.1 Sol
DevRev uses GPT-6.1 Sol to power Computer and Operator agents for enterprise self-service, balancing reasoning, speed, and cost.
-
OpenHands downloads down 36% in a week
45.6K PyPI downloads in the 7 days to Nov 4, against 71.2K the week before.
-
Api downloads up 41% in a week
44.4K npm downloads in the 7 days to Nov 4, against 31.6K the week before.
-
Checksum downloads up 71% in a week
20.7K npm downloads in the 7 days to Nov 4, against 12.1K the week before.
-
Noetic downloads up 581% in a week
23.7K npm downloads in the 7 days to Nov 4, against 3,480 the week before.
-
BrowserSkill passes 10K GitHub stars
-
dsh-Go passes 10K GitHub stars
-
Anatomy gained 2,782 GitHub stars in a week
Now at 25K stars.
-
Day Trader Skill gained 2,653 GitHub stars in a week
Now at 5,359 stars.
-
Horizon gained 1,702 GitHub stars in a week
Now at 12.7K stars, against about 391 a week over the month before.
-
Learnharness gained 1,735 GitHub stars in a week
Now at 5,414 stars.
-
Openbot gained 2,214 GitHub stars in a week
Now at 5,601 stars, against about 772 a week over the month before.
-
Solidcraft gained 2,124 GitHub stars in a week
Now at 13.8K stars.
-
datasette-agent 0.5a0
datasette-agent 0.5a0 adds a panel feature enabling the agent chat to sit beside Datasette pages for real-time app modification.
-
Dependabot version updates support Agent Package Manager
Dependabot now supports version updates for Agent Package Manager, allowing automated updates to AI agent skills, prompts, and instructions.
-
Agentic cheminformatics with Google Antigravity
Google Antigravity accelerates drug discovery workflows with cheminformatics skills for searching compounds and proposing novel macrocycles.
-
Build a semantic layer for agentic AI with EDB Postgres AI and Amazon Bedrock AgentCore
EDB Postgres AI and Amazon Bedrock AgentCore enable building a semantic layer for agentic AI with governed access control for Strands Agents.
-
Langfuse 3.227.0 released
feat(blob-export): add opt-in trace field groups for the legacy traces export (v3 backport of (+3 more releases that day)
-
Same Model, Different Harness: CUGA, Hermes, and Deep Agents — When to Pick CUGA?
Comparison of agent frameworks CUGA, Hermes, and Deep Agents discussing when to use each.
-
Junie 3959.5 released
Fix the process hanging and disk filling up and memory leak; Fix of the crashes due to an excessively large output string; Fix of the error that blocked interaction with models (+12 more releases that day)
-
GitHub Copilot is now available in JetBrains Air
GitHub Copilot is now available in JetBrains Air, using the Agent Client Protocol for coding task delegation and execution.
-
Lindy pricing changed: Free + $49.99/mo → $29.99/mo
Per active user with shared team credit pool: Team plan starts at $29.99/month for 3,000 credits, scaling up to $9,999.50/month for 1,750,000 credits. Top-ups at $10 per 1,000 credits. Enterprise custom pricing. Free trial: $50 in credits for 7 days, no card r
-
Cloudflare Agents SDK 0.33.0 released
Pi 1.5 support: agents/harness/pi, agents/models/pi-ai and the Pi tools now run on Pi 1.5.; Far fewer storage writes while streaming: Pi stores streamed answers and tool output in batches, at the latest every second, instead of on every update.; Faster with…
-
Context7 4.5.0 released
MCP Bundle for @upstash/context7-mcp@4.5.0 (+2 more releases that day)
-
[AINews] LLMs can read & write neural network weights: "Weight Space Programming" cuts Autoresearch out of the RSI loop
Research demonstrates LLMs can directly manipulate neural network weights, with applications to reducing reasoning loops in models like Qwen and DeepSeek's agent prototypes.
-
Pydantic AI 2.65.0 released
Protect the gh-aw canonical session capture from agent tools; Add multimodal notes to AskUserAnswer; Count BrowserUse model calls toward the host run's usage and UsageLimits
-
Loki Mode downloads down 61% in a week
20.2K npm downloads in the 7 days to Nov 3, against 51.8K the week before.
-
Cognee downloads up 31% in a week
36.9K PyPI downloads in the 7 days to Nov 3, against 28.1K the week before.
-
Context7 downloads up 33% in a week
741K npm downloads in the 7 days to Nov 3, against 558K the week before.
This list shows notable items; the sections above show everything of their kind, including patch releases of smaller projects and low-impact incidents. Summaries of outside articles are written automatically from the source's own text and may miss nuance, so follow the link before relying on one.