Agent Framework
Stories, products, and related signals connected to this tag in Explore.
Stories
Filter storiesOpenAI says the Codex SDK lets applications retain their interface, context, tools, and approval controls while its harness runs the agent loop. A tax-preparation pilot processed 7,000 returns with the setup.
Vercel Labs open-sourced fx, an Apache-2.0 CLI and harness for coding-agent research and embedding. Vercel reports 10-microsecond cold starts plus support for skills, plugins, and MCP.
LangChain opened Managed Deep Agents in public beta for scaffolding agents with channels, sandboxes, memory, and identity. The agents deploy on LangSmith-managed infrastructure with evals and lifecycle controls.
Teknium shipped the Herald release of Hermes Agent as a desktop-agent and runtime update. The release adds voice chats, desktop plugins, Agent2Agent/webhooks, productivity skills, grounded research, Ironproxy secrets lockdown, and trace-driven token-efficiency work from 250,000 conversations.
Poolside launched Desktop Assistant for macOS, VS Code, and Visual Studio. It can run compatible agents such as Poolside, Claude Code, and Codex across parallel worktrees while handing off context.
New releases and practitioner posts described graph-shaped agent runtimes instead of simple loops. Slate, LangChain's open-sourced agent factory, and AI SDK's Python package each add pieces for durable orchestration.
Anthropic published Claude Managed Agents examples for long-running production agents. The patterns cover outcome rubrics, self-correction, and sharing sandbox context between agents.
AI21 says its pipeline routes exploration, extraction, and patching across model tiers and reaches 80.8% on SWE-Bench Pro at $5.99 per task. Other workflows use critic agents, readable harnesses, Fugu/Nemotron routing, and scheduled Gemini agents.
LingBot 2.0 released code and weights for a real-time world model and robot-action models. The VLA maps 20 robot body configurations into a 55D action format and filters 90,000 raw robot hours to 50,000 training hours.
Threads and papers traced agent reliability failures to harness details including tool schemas, state, retries, logs, and effort-level evals. Examples included Claude Code test loops, MCP server patterns, and OctoTools.
Vercel introduced eve in public preview with durable workflows, sandboxed compute, subagents, and evals. It also added Connect and Passport for scoped tokens and identity-gated deployments, giving teams one path for runtime, auth, and enterprise access control.
Flue 1.0 Beta reorganizes the framework around workflows, autonomous agents, and channel connectors while keeping model-agnostic deployment. The release gives TypeScript teams a more opinionated base for durable, long-running agents.
agent-tui shipped v0.2.0 with markdown rendering, tool approvals, configurable reasoning views, and an AI SDK-only dependency chain. The demo also showed Gemma 4 31B running locally, so the terminal UI now covers hosted and on-device models.
Flue previewed a command that points at docs or SDK URLs and has the agent write a sandbox connector directly into your codebase without extra packages. Follow-on tweaks, a Python port, and Unkey deploy support show the harness is becoming a testbed for self-authored integrations.
Flue launched as a runtime-agnostic TypeScript framework for headless agents, with Claude Code-like harness behavior but no built-in GUI and most logic living in Markdown skills and AGENTS.md. Early demos show a 43-line starter that can expose an agent service, highlighting a push to separate harness logic from chat interfaces.
CopilotKit released A2UI v0.9 for declarative generative UI, where agents emit JSON and frontends render from a component catalog. The update adds AG-UI support, live incremental rendering, and a shared web core across React, Angular, Flutter, and Lit.