Search Results for "evidence"
Sort By:
Showing 21 open source projects for "evidence"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
HowToLiveBetter
Evidence-based living guidelines sorted by cost-effectiveness
HowToLiveBetter is an evidence-focused interactive life guide that organizes hundreds of practical recommendations by cost, expected benefit, and strength of evidence. It covers health, longevity, emergency response, personal finance, legal risks, unemployment, entrepreneurship, relationships, parenting, travel, and skill development. Each recommendation explains what resources it costs and what outcome it is intended to improve. -
2
Better Harness
Help your coding agents get better at getting better
...Instead of reviewing only the final code change, it examines how an agent understood the task, executed work, validated results, delivered safely, and captured reusable lessons. It gathers project and session evidence while marking missing or unobserved behavior explicitly. Reports organize findings across five Agent Work Loop dimensions and connect each conclusion to visible supporting evidence. Supported gaps become prioritized recommendations with expected outcomes, repair boundaries, and acceptance checks. Repeated reports can be compared through a history view to observe workflow trends without claiming unsupported causation. ... -
3
unlazy
Anti-laziness skill for AI agents. Core: the Depth Tree method
...It requires agents to define acceptance gates before claiming that work is finished. Each gate can specify a command, expected result, working directory, and recorded evidence. A bundled checker validates the ledger, runs approved checks, and can reverify previously completed work. The workflow emphasizes reviewing returned work and reporting only conclusions supported by verifiable evidence. It can be installed for Claude Code, Codex CLI, and other skill-compatible agents, with additional templates and orchestration guidance for more complex tasks. -
4
Loop Library
A library of practical AI-agent loops and an installable skill
...The repository contains both a public loop library website and the Loopy skill that agents can use to discover, audit, adapt, run, and prepare loops. It helps turn open-ended prompts into measurable workflows with evidence, stopping criteria, and human approval points. The skill can work with agent environments such as Codex, Cursor, and Claude Code through the Skills CLI. Overall, it is useful for teams that want safer, reusable, and more reliable agent workflows instead of one-off prompting. -
Build Data Resilience - Take the Assessment TodayIs your recovery strategy as strong as you think? Take this quick self-assessment to check your recovery readiness and gain tailored insights. In only 2 minutes, you'll learn where you fall on the recovery readiness scale.
-
5
BrowserTools MCP
Monitor browser logs directly from Cursor
...It can capture console/network logs, DOM snapshots, and screenshots, and expose them as typed resources the agent can query or act on. The design aims to make IDE agents (e.g., Cursor, Claude Desktop) more “web-aware,” enabling workflows like reproducing a bug, collecting evidence, and proposing fixes without copy-pasting. Documentation and community guides outline a quick setup, including the extension, the MCP server process, and common troubleshooting steps. The project is actively maintained, with public commit activity and discussions around connectivity and reliability in different IDEs. Overall, it bridges the gap between local coding agents and the real browser they need to observe and manipulate. -
6
Marble Skill Taxonomy
Structured taxonomy of what children learn across the primary years
...It breaks curriculum content into fine-grained micro-topics instead of leaving learning goals as broad standards. Each topic includes subject, domain, age range, description, evidence criteria, assessment prompt, and stable identifiers. The dataset also defines prerequisite relationships, so developers can trace what a learner should master before a concept. It aligns micro-topics to national curriculum standards such as NGSS, Common Core, and the UK National Curriculum. It is useful for learning platforms, curriculum tools, tutoring systems, assessment products, and education research projects. -
7
security-audit
A coding-agent skill for multi-phase security audits
...The skill produces human-readable reports, detailed finding traces, structured JSON output, and independent verification against the actual source code. Overall, it is designed to make AI-assisted security review more systematic, adversarial, and evidence-based. -
8
Deep Research
Use any LLMs (Large Language Models) for Deep Research
...It offers MCP server support and SSE APIs, so IDEs and agent clients can drive the same workflow programmatically. The result is a repeatable process for scoping questions, collecting evidence, and producing a concise report with citations and reasoning steps. -
9
Tonic
Easy to audit, zero-dependencies and build-tool-free
...Tonic has no templating language, it uses HTML! But since HTML only understands string values, we need some help to pass more complex values to a component, for that we use this.html. There is no evidence that Virtual DOMs improve performance across a broad set of use cases, but it's certain that they greatly increase complexity. Tonic doesn't use them. Instead, we recommend incremental updates. -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
10
paytia-saq-checklist
Free, plain-English PCI DSS SAQ checklists. SAQ A, A-EP, B, and D
...If you're a finance director or operations manager who's suddenly responsible for PCI compliance, they're rough going. This project translates the highest-impact controls from SAQ A, A-EP, B, and D into language a busy ops manager can use, with the evidence you'll need to gather for each one. WHAT'S INSIDE - 8-step decision guide to work out which SAQ actually appl -
11
UVU
UVU is an extremely fast and lightweight test runner for Node.js
UVU is a lightweight, ultra-fast JavaScript test runner for Node.js and the browser created by Luke Edwards (lukeed). Its primary goal is to minimize overhead: startup time, memory usage, and complexity are all kept very low so that developers can write and run tests with minimal friction. The tool supports modern features like async/await and native ES Modules, making it suitable for modern codebases. It also supports running in browser environments, which makes it versatile for frontend... -
12
Atom Linux
The hackable text editor
...We designed it to be deeply customizable, but still approachable using the default configuration. A set of encrypted code signing certificates were exfiltrated; however, the certificates were password-protected and we have no evidence of malicious use. As a preventative measure, we will revoke the exposed certificates used for the Atom application. Revoking these certificates will invalidate some versions of Atom. When we introduced Atom in 2011, we set out to give developers a text editor that was deeply customizable but also easy to use—one that made it possible for more people to build software. ... -
13
Ants-Review
A Protocol for Open Anonymous Scientific Peer-Reviews on Ethereum
The Project implements a Bounty-like protocol called Ants-Review to allow issuers to issue an AntReview, a bounty for peer-review in scientific publication, linked to requirements stored on ipfs which peer-reviewers can fill by submitting the ipfs hash which contains evidence of their fulfillment. After the submission of successful peer-reviews, they will be approved by an approver and payed in ANTS. AntReview Issuers are addresses, added by the owner of the contract, that can issue an AntReview via the function issueAntReview(). AntReview Approvers are addresses added by Issuers when they issue an AntReview or with the function addApprover(). -
14
Headless Chrome Crawler
Distributed crawler powered by Headless Chrome
...Powered by Headless Chrome, the crawler provides simple APIs to crawl dynamic websites. Support both depth-first search and breadth-first search algorithm. Save screenshots for the crawling evidence, emulate devices and user agents, priority queue for crawling efficiency, obey robots.txt, and more. The static crawlers are based on simple requests to HTML files. They are generally fast, but fail scraping the contents when the HTML dynamically changes on browsers. Dynamic crawlers based on PhantomJS and Selenium work magically on such dynamic applications. ... -
15
Pour la médecine fondée sur les faits (Evidence-Based Medicine (EBM)). La technique PICO pour formuler des questions cliniques. Plate-forme web open source pour supporter la création de PICO, la recherche et l'évaluation d'informations.
-
16
i20k (ISO 20000 SoftWare)
i20k SW de Gestión del Servicio ISO 20000
...Powered by SOITSA (www.soitsa.com), its structure is the same as the ISO standard and its features facilitate continual service improvement and generate the necessary evidence for internal audits and certification. i20k has been recognized as an excellent software in the testing phase by certified auditors. -
17
TaxManager umožňuje vystavit faktury, příjmové a výdajové doklady a další doklady nutné k vedení daňové evidence. Umožňuje také výpočet očekávané daně + plateb za sociální a zdravotní pojištění.
-
18
Ice Coral - WorkLog
Work diary to make an evidence of device servicing
This is a part of the Ice Coral project. The WorkLog is focused on evidence of device servicing. It's good for service teams to share information about done work. For more information visit Ice Coral - WorkLog Web Site link below. -
19
PiAnoS is a powerful pedagogical web-interface developed by the University of Lausanne/School of Criminal Justice dedicated to the characteristics annotation made by forensic examiners on evidence and reference images during the individualization process
-
20
Ice Coral - TimeSpan
Scheduled task and device event evidence
This is a part of the Ice Coral project. The TimeSpan is focused on event evidence, for example scheduled tasks (Windows Task Scheduler, crond). For more info visit Ice Coral - TimeSpan Web Site. -
21
Ice Coral (project)
Information system for network infrastructure
Ice Coral is intended to take place as Information System for InfraStructure (ISIS). This project should be central information evidence about your network infrastructure. It's planned as modular system, so you can use only one part of this system (eg. WorkLog), if you want. For more info visit Ice Coral (project) Web Site link below.
- Previous
- You're on page 1
- Next
