AI Agent News: Releases, Launches and Usage Jumps, Live · page 30
-
Hindsight passes 50K GitHub stars
-
Horizon passes 10K GitHub stars
-
PentAGI passes 30K GitHub stars
-
PicoClaw passes 30K GitHub stars
-
Rea gained 246K GitHub stars in a week
Now at 283K stars, against about 7,550 a week over the month before.
-
Xerj gained 2,510 GitHub stars in a week
Now at 6,061 stars, against about 380 a week over the month before.
-
LFM2.5-24B-A2B: Built for fast on-device agents
Liquid AI released LFM2.5-24B-A2B, a model designed for fast on-device agents.
-
Junie 3800.1 released
(+14 more releases that day)
-
Headroom 0.41.0 released
antigravity: add native Google Antigravity IDE integration (#3817) (cd4367b); opencode: support the OpenCode 2.x plugin API (#3999) (1d4b357); plugins: add headroom-snip Claude Code mod that animates compression (#3980) (17abee2)
-
Bland AI: LLM outage - Widespread agent silence
Critical impact; resolved after 55 min.
-
Oh My Pi 18.11.0 released
Removed ApprovalDetailsOptions; formatApprovalDetails takes only args again, since the compact approval prompt no longer shows tool details; AgentTool.delegationGuidance: instructions a same-name extension replacement inherits in its description when it…
-
Crossing the Threshold: How OpenAI and Anthropic Approach Autonomy and Safety in Financial Agents
At AI Engineer New York, frontier labs and financial firms explored how to give agents useful autonomy while keeping consequential decisions under control.
-
Crossing the Threshold: How OpenAI and Anthropic Approach Autonomy and Safety in Financial Agents
OpenAI and Anthropic discussed approaches to agent autonomy and safety in financial applications at AI Engineer New York.
-
Strands Agents 1.61.0 released
feat(skills): package Strands for Claude, Codex, and Cursor (#5123) (5e84cafc7); feat(ts): add DecisionModel primitive and LLMDecisionModel (#4942) (8340c4241); feat(mcp-ts): add progress callbacks for tool calls (#4302) (5eaf888f6) (+4 more releases that day)
-
Show HN: Graphicle, a Rust port of Graphify with memory for coding agents
Graphicle is a Rust implementation of Graphify that adds memory capabilities for coding agents.
-
Qodo: Automatic PR reviews not triggered for some single-tenant customers
Major impact; resolved after -3 h 58 min.
-
Qodo: Degraded performance for AI reviews
Critical impact; resolved after -24 h 45 min.
-
Rea 6.5.0 released
Analyze selected JavaScript files and recover cross-bundle relationships without expanding the selected source scope.; Read compact summaries and page retained Evidence across binary, managed, Android, Dart, WASM and network workflows.; Inspect SQLite…
-
Amp puts AI agents to work beyond code with OpenAI models
Amp demonstrates AI agents using OpenAI models including GPT-6 Astra, Ultrafast, and GPT-Live-1.
-
Langfuse 4.59.0 released
feat(llm-connections): label TypeSafe adapter as "TypeSafe (System One)" in picker; perf(worker): poll queue metrics once per interval across workers; ci(notifications): stop sending redundant title, branch, and event to Slack
-
Cursor CLI pricing changed: Free + $20/mo → Free + $8/mo
No separate CLI price; it uses Cursor plans, which Cursor now sells together with X features: Free (limited agent requests), Plus $8/month (Grok models only), Premium $30/month, Super $100/month, Ultra $200/month, Teams from $30/user/month, Enterprise custom.
-
Qodo: Automatic PR reviews not triggered for some single-tenant customers
Major impact; resolved after 0 min.
-
Mastra 1.77.0 released
Factory projects now support provider-instance sandboxes (MastraFactoryConfig.sandbox) for settings/builds; existing callback form still works but lacks these capabilities.; @mastra/server workflow HTTP routes no longer allow starting/resuming internal…
-
How Third Moment Research runs 10,000 agents for 36+ hours
Third Moment Research runs 10,000 agents for extended periods using OpenAI models, focusing on agents that improve with use over time.
-
[AINews] AI Engineer NYC: Gemini 4 Argon, Vals AI Benchmarks
Gemini 4 Argon went GA today, but we already gave it title story 2 weeks ago and most benchmarks, like CursorBench, simply independently confirm their claims.
-
The EU’s next chapter in AI is agentic
Analysis shows agentic AI adoption is growing among EU enterprises and small businesses, with potential for deeper use.
-
Momentic downloads down 34% in a week
119K npm and PyPI downloads in the 7 days to Oct 14, against 179K the week before.
-
Context7 downloads up 42% in a week
829K npm and PyPI downloads in the 7 days to Oct 14, against 586K the week before.
-
DeepSeek Harness downloads up 38% in a week
329K npm and PyPI downloads in the 7 days to Oct 14, against 238K the week before.
-
Grok Build downloads up 28% in a week
58.7K npm and PyPI downloads in the 7 days to Oct 14, against 45.9K the week before.
-
nanobot downloads up 38% in a week
21.6K npm and PyPI downloads in the 7 days to Oct 14, against 15.6K the week before.
-
OpenShell downloads up 48% in a week
131K npm and PyPI downloads in the 7 days to Oct 14, against 88.3K the week before.
-
Anatomy passes 10K GitHub stars
-
Rea passes 250K GitHub stars
-
Trail-Code passes 10K GitHub stars
-
Dsh Ops gained 1,869 GitHub stars in a week
Now at 1,996 stars.
-
Pydantic AI 2.56.0 released
Run BrowserUse on the host model by default and make browser-use telemetry opt-in; Let Skills layer project and personal libraries, name each skill's directory, and render a skill for a host command; Add baseurl argument to ZaiProvider
-
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Our first robotics pod with Dyna’s Chief Scientist on their big bet on World Action Models & the Next Frontier of Physical AI
-
Gemini CLI 0.64.0 released
refactor(a2a-server): implement V1 to V2 settings migration logic; fix(acp): bridge PromptResponse.usage and emit usageupdate notifications; Changelog for v0.63.0-preview.0
-
Building agents that transact with Anchor Browser and AgentCore payments
AWS Bedrock AgentCore payments enables AI agents to autonomously pay for resources while managing budgets and signing transactions without exposing credentials.
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.