GitHub Repo

GitHub 熱門專案、開源工具、框架、runtime 與重要 release。

Grafana Agent Observability Reaches General Availability, Connecting Online Evaluation and Agent CI Through Open-Source SDKs

Grafana has made its internally used agent observability platform generally available and released the open-source agento11y SDK, which supports five languages and multiple agent frameworks. The platform brings conversations, tool execution, costs, OTel traces, online evaluation, and offline experiments into a unified regression workflow, although the complete product remains tied to Grafana Cloud.

2026-08-01

代理工具

RepoComplianceBench: Four Coding Agents Almost Never Proactively Read Open-Source Projects’ AI Contribution Rules

The study tested refusal, disclosure, verification, and human-handoff rules across 106 tasks from 49 real repositories. By default, all four frontier models rarely searched for policies proactively. Explicit rules or added validators improved disclosure and testing, but under every tested condition, the agents failed to comply with requirements prohibiting AI contributions.

2026-08-01

代理工具

MANTA Reconfigures Multi-Agent Topologies Mid-Inference, Improving the Five-Benchmark Average by 5.8 Points

MANTA builds an agent communication graph for each task, then detects collaboration anomalies from execution traces and makes constrained changes to roles, connections, and verification order. Tested with Gemma 4 31B, it achieved an average score of 74.0 across five benchmarks, although the number of samples and repeated runs remained limited.

2026-07-31

推論系統

Local LLM Testing on M4 Max: Faster Decoding Than GB10, but Full Responses Remain Constrained by Prefill

A new round of similarly priced local AI testing shows that the M4 Max, with 546GB/s of unified memory bandwidth, leads the GB10 and Strix Halo in per-token decoding across three quantized models. The GB10 still has the advantage in prompt prefill and overall energy efficiency, demonstrating that tokens/s alone can misrepresent actual response times.

2026-08-01

開發者平台／API

GitHub Models Officially Shuts Down, Taking Its Inference API, Model Catalog, and BYOK Offline

GitHub shut down the Models playground, model catalog, inference API, and bring-your-own-key functionality on July 30, including for existing paying users. Applications that depend on its endpoints must migrate to Microsoft Foundry, another model gateway, or an in-house provider abstraction layer.

2026-07-23

代理工具

Reassessing Five Computer-Agent Benchmarks: 15.3% of Failure Judgments Were Actually Wrong

Researchers manually reviewed 150 public trajectories labeled as failures and found that 10.7% were grader false negatives, while another 4.7% resulted from impossible tasks. Genuine failures also occurred mainly in planning and outcome verification—not mouse targeting or tool execution.

2026-07-31

AI 安全

MIND Filters Agent Memory with an Intent Information Bottleneck, Cutting Attack Success Rates by More Than 55% on Average

Rather than invoking a large model to review each memory individually, MIND compares compressed representations of the original intent and subsequent behavior, then uses a multi-hyperplane classifier to intercept poisoned content. Controlled experiments with four models showed lower attack success rates and average latency close to the undefended baseline, although the code has not yet been released.

2026-07-31

AgenticASR Repeatedly Revises Transcripts With a Sliding Window, 1B Refiner Pushes Bilingual Benchmark Score to 79.95

AgenticASR separates speech recognition from text cleanup, allowing a small Refiner to rewrite a limited portion of existing output as new speech arrives, without repeatedly processing the full transcript. The code, checkpoints, and a 917-item Chinese-English benchmark are publicly available, but most of the audio is synthetically generated and scoring relies on an LLM judge.

2026-07-31

推論系統

QuantWAMs Runs World Action Models Primarily at 4-bit, Targets 29% of FP16 Memory Usage for Key Modules

For models that generate future frames and robot actions simultaneously, QuantWAMs turns quantization calibration into a three-level decision process covering structure, joint objectives, and closed-loop trajectories. The simulated success rates of two models were within 0.2 to 0.7 percentage points of FP16, but the speed measurements cover only specific compute modules, while each real-robot comparison involved just ten trials per task.

2026-07-31

代理工具

Increasing the Inference Budget for Local Computer Agents Does Not Necessarily Improve Accuracy, With Benefits Reversing After Four Historical Screenshots

An OSWorld experiment shows that giving local GUI agents a small amount of screen history can substantially reduce repeated actions, but further extending the context or step limit mainly changes the types of failure. A two-stage planning architecture also trails a single agent because of formatting and coordination overhead, while generating more plans in parallel recovers only part of the gap at a high token cost.

2026-07-31

代理工具

Qwen-UI-Agent Unifies Mobile, Desktop, and Browser Operations, Extending Long-Trajectory Training Beyond 100 Steps

The Qwen team has introduced a unified GUI agent spanning mobile, desktop, web, and DeepSearch environments, with on-screen interactions and CLI commands sharing the same action space. Its technical report claims a score of 79.5% on OSWorld-Verified, but the model weights, training data, and complete trajectories have not yet been released.

2026-07-31

代理工具

OSReward Finds That Computer-Agent Judges Commonly Let Failed Trajectories Pass, While Visual Evidence Has Surprisingly Limited Impact on Verdicts

Using 1,019 human-reviewed cross-platform trajectories, OSReward tested 27 vision-language judges and found that their main error was classifying incomplete tasks as successful. Removing step-by-step text reduced accuracy by an average of 7.2 percentage points, while changing the visual inputs had a smaller effect, exposing current “visual judges’” reliance on agents’ self-reported narratives.

2026-07-31