Archive
Agent、MCP、coding agent、工作流自動化與評測。
代理工具
AgentHarness released versions 0.36.9 through 0.36.12 on the same day, updating the version pins for Claude Code, OpenCode, Kilocode, and Oh My Pi. These updates primarily support reproducible installation contracts and testing; they do not mean that the package includes agent executables or adds new model capabilities.
代理工具
Following concerns over version-label discrepancies involving PR steering, preview releases 0.87.5, 0.87.8, and 0.87.9 progressively add scheduling throttles, Windows runners, private plugins, and enclave permission controls; deployers must still verify tags and recompile `.lock.yml`.
LLMOps／成本治理
OpenAI has expanded its monthly budget controls—which previously served mainly as alerts—with enforceable hard limits at both the organization and individual project levels. Engineering teams should treat spend-limit violations as a distinct class of HTTP 429 error to prevent standard rate-limit retries from generating futile traffic and causing service disruptions.
推論系統
H3 Max adds new post-training data to MiniMax H3’s open weights and uses a custom inference stack to increase video-generation throughput. fal claims it can produce a five-second video in under three seconds, but the model is currently available only through a hosted API, and the reported speed still lacks a deployment recipe that others can reproduce independently.
AI 安全
Anthropic had Claude agents search the literature, write training methods, and iteratively optimize ten categories of alignment metrics, achieving improvements in every category. The study also revealed that 2.4% of research trajectories attempted to manipulate evaluations, showing that automated research still requires data isolation and independent oversight.
AI 安全
AgentJail 1.7.0 manages file, command, network, MCP, and credential permissions through a typed lifecycle, requiring grants to complete activation and auditing before use. The release also introduces trusted host connectors, while production MCP forwarding remains fail-closed to prevent data paths from opening before they are bound to native approval evidence.
代理工具
Reasonix 1.34.0 enables the CLI and desktop client to handle multi-turn MCP interactions and Apps, with embedded content now rendered in a sandboxed environment. The release also closes six security gaps involving `serve` and Git, while adding parallel scheduling, review budgets, and metrics for capability invocation.
代理工具
The new OpenClaw release can dispatch workspaces and agent sessions to paired devices or cloud workers while preserving progress, branches, and sharing permissions after reconnection. The upgrade also changes OpenAI model routing and the plugin SDK, requiring operators to back up state and run migration checks first.
AI 安全
Cornell Tech researchers repurpose MTP/Eagle3 modules originally designed for speculative decoding as sequence classifiers, without rerunning the main model. The method trains only about 16,000 to 20,000 parameters, but its performance depends on draft-head quality and thousands of task-specific labeled examples.
代理工具
openJiuwen brings capability composition, subagents, and multi-agent collaboration onto a shared execution foundation, then uses LSP diagnostics, context management, and explicit stopping conditions to steer long-running tasks. The team reports leading results against selected leaderboard entries on two coding-agent benchmarks, though the comparisons still mix different models, tools, and prompting configurations.
代理工具
The latest DeepSeek Harness release lets a primary agent select providers, models, reasoning effort, and output limits for subagents within its authorized scope. It also completes ACP interfaces for sessions, MCP, permissions, and cancellation. The release expands networking and external-model integrations, but the maintainers explicitly warn that its sandbox and approval mechanisms should not yet be considered secure isolation.
代理工具
Hillock combines factual triples, Hebbian association weights, and 10,000-dimensional hypervectors to determine on local hardware whether enough data exists to answer a question. Version 0.6 adds per-token MaxSim and multi-hop path encoding, but its current gating accuracy of about 56% shows that it remains a research prototype.