coding agents
Together AI Discloses Prompt Leakage After a Dragos Study
Together AI discloses prompt leakage of stored samples after a public credential exposure. OpenRouter found no breach of itself; Novita cites a routing issue.
Latest
Carta Evergreen Opens Multiplayer AI Coding for Teams
Carta Evergreen: multiplayer AI coding with agents; Carta cites ~20k PRs/week and lower reverts. Usage fees: $0.15/M tokens plus provider price.
Cognition Says Devin Review 2.0 Cuts PR Review Cost 82%
Devin Review 2.0: Cognition says PR review cost down 82% since August; typical $0.25–$0.75. Company metrics, not independent benchmarks.
Ricursive Releases Ripple-65B Preview Open Weights
Ricursive Intelligence released Ripple-65B Preview open weights. It claims 80.52 on TerminalBench 2.1 among US peers and a $32M R&D cost.
Meituan’s LongCat-2.5 AI Model Was Trained Only on Chinese Chips
Meituan's LongCat-2.5 is a 1.6tn-parameter multimodal model trained on Chinese chips. Its own benchmarks show wins and clear losses against Claude.
DeepSeek Open-Sources a Superagent That Works Inside a GitHub Repo
DeepSeek superagent prototype is out under MIT: a research coding agent that takes requests on GitHub or Feishu and replies with pull requests.
Google Is Shutting Jules; Sessions End 11 November, Export Opens Now
Jules shutdown: Google's coding agent goes read-only after 11 November and closes on 31 December. How to export sessions, memories and settings now.
Factory Says Droid 1.0 Beats Codex and Claude Code in Its Own Tests
Factory's Droid 1.0 coding-agent harness makes scripted tool calls the default. Its own Terminal-Bench 4 runs put it ahead of Codex and Claude Code.
GitLab Orbit Goes GA, Claiming Up to 45x Fewer Agent Retries
GitLab Orbit, a context graph for AI coding agents, is now GA. GitLab says its tests showed up to 45x fewer retries and 4.5x fewer tokens.
Mistral Opens Large 4 Weights: a 1-Trillion-Parameter Model
Mistral has released the weights of Large 4, a 1-trillion-parameter multimodal model, and warns its cyber skills carry a potential for real attack uplift.
Particle-1 Coding Model Uses About 45% Fewer Tokens, Particle Says
Suhail Doshi's Particle has launched Particle-1, a DeepSeek V4.1 Flash coding model it says uses about 45% fewer tokens with similar accuracy.
Timeline
Every story in coding agents, grouped by month.
November 2026
- 22 Nov 2026: Together AI Discloses Prompt Leakage After a Dragos StudyTogether AI discloses prompt leakage of stored samples after a public credential exposure. OpenRouter found no breach of itself; Novita cites a routing issue.
- 17 Nov 2026: Replit Launches Missions, Agent Swarms With Spending CapsReplit has launched Missions, which it says runs agent swarms toward a goal within a budget, with spending caps and approve-before-publishing controls.
- 17 Nov 2026: Cognition Launches Devin Bots to Lead Teams of AgentsCognition has launched Devin Bots, persistent agents it says can lead teams of Devins and bring engineers only the decisions that need their judgment.
- 17 Nov 2026: Mistral Launches Vibe Desktop for macOS and WindowsMistral has launched Vibe Desktop for macOS and Windows, combining Work and coding in one app. Linux is coming soon; no separate CLI install…
- 7 Nov 2026: OpenRouter Launches Auto Code and Rebuilds Its Auto RouterOpenRouter Auto Code selects models for coding agents. The company reports lower cost per task in five benchmarks; model usage is still charged.
- 6 Nov 2026: Carta Evergreen Opens Multiplayer AI Coding for TeamsCarta Evergreen: multiplayer AI coding with agents; Carta cites ~20k PRs/week and lower reverts. Usage fees: $0.15/M tokens plus provider price.
- 6 Nov 2026: Cognition Says Devin Review 2.0 Cuts PR Review Cost 82%Devin Review 2.0: Cognition says PR review cost down 82% since August; typical $0.25–$0.75. Company metrics, not independent benchmarks.
- 5 Nov 2026: Ricursive Releases Ripple-65B Preview Open WeightsRicursive Intelligence released Ripple-65B Preview open weights. It claims 80.52 on TerminalBench 2.1 among US peers and a $32M R&D cost.
- 2 Nov 2026: Meituan's LongCat-2.5 AI Model Was Trained Only on Chinese ChipsMeituan's LongCat-2.5 is a 1.6tn-parameter multimodal model trained on Chinese chips. Its own benchmarks show wins and clear losses against Claude.
October 2026
- 31 Oct 2026: DeepSeek Open-Sources a Superagent That Works Inside a GitHub RepoDeepSeek superagent prototype is out under MIT: a research coding agent that takes requests on GitHub or Feishu and replies with pull requests.
- 30 Oct 2026: Google Is Shutting Jules; Sessions End 11 November, Export Opens NowJules shutdown: Google's coding agent goes read-only after 11 November and closes on 31 December. How to export sessions, memories and settings now.
- 30 Oct 2026: Factory Says Droid 1.0 Beats Codex and Claude Code in Its Own TestsFactory's Droid 1.0 coding-agent harness makes scripted tool calls the default. Its own Terminal-Bench 4 runs put it ahead of Codex and Claude Code.
Load more Showing 12 of 52
Related stories
Latest from topics connected to coding agents. See all with connected topics
Latest on TSN
Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.
