Search Results for "evidence"
Sort By:
Showing 16 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.
-
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
1
Harness-1
Ultra Recipe for Training Long-Horizon Search Agents
Harness-1 is a 20B search agent trained with reinforcement learning inside a stateful retrieval harness. It is designed for long-horizon search tasks where the model must search, inspect documents, curate evidence, verify claims, and decide when enough evidence has been gathered. The harness externalizes search state, including candidate documents, evidence links, verification records, and budget-aware context. This lets the policy focus on higher-level decisions instead of trying to keep every detail inside the model context. The repository includes inference utilities, training scripts, evaluation runners, dataset tools, and documentation for running the released checkpoint. ... -
2
The Fable Method
How Claude Fable 5 worked, distilled into skills
...It converts observed problem-solving habits into explicit steps that different language models can follow. The core process classifies the request, defines completion criteria, gathers primary evidence, chooses one recommendation, makes the smallest correct change, and verifies the result. Four included skills cover planning, execution, judging completed work, and generating domain-specific adapters. The repository preserves evaluation cases, raw judge outputs, failures, and results from hundreds of agent runs. Its rules include bounded retries, authorization gates, evidence requirements, and honest caveat reporting. ... -
3
HOL Guard
Open-source antivirus for AI agents
...It integrates with major coding agents including Claude Code, Codex, Cursor, Gemini CLI, OpenCode, and GitHub Copilot CLI. Local operation requires no cloud account, while optional cloud services add synchronized evidence, shared policies, fleet visibility, and team approvals. -
4
geo-sleuth
An agent skill that finds where a photo was taken
...Specialized Python scripts collect, score, and rank geographic candidates before the AI agent evaluates the strongest matches. Results include estimated coordinates, camera direction, confidence levels, and supporting visual evidence. Geo-Sleuth integrates with Claude Code, Codex, Cursor, Gemini CLI, OpenCode, and GitHub Copilot. -
Build Securely on Azure with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
5
CyberPPT
A Codex Skill for generating high-density, editable PowerPoints
CyberPPT is a Codex Skill for converting documents, research, and business data into dense, editable, consulting-style PowerPoint presentations. It extracts facts, numbers, claims, recommendations, conflicts, and caveats from formats such as PDF, DOCX, TXT, and XLSX. The workflow builds an MBB-style evidence table before developing storylines and converging on an SCR narrative. Users select from eight fixed visual systems, after which the skill plans each slide’s hierarchy, grid, charts, palette, and information density. Image-generation blueprints guide reconstruction while native text, shapes, tables, charts, and vectors preserve core editability. ... -
6
VulnClaw
Based on AI Agent + MCP toolchain + penetration Skill orchestration
...Its newer architecture uses a goal-driven solving engine instead of a fixed-round loop, helping the agent stop when the goal is reached, the search space is exhausted, or a safety budget is met. It also includes evidence checks designed to reduce hallucinated conclusions by requiring real tool output before accepting key findings. VulnClaw is intended for authorized testing, CTFs, security education, and controlled red-team environments. -
7
AutoCVE
Agent-driven automated CVE discovery platform for source code auditing
...Users can choose enhanced scanning, intelligent auditing, or comprehensive auditing based on speed and depth requirements. The interface records agent trees, tool calls, phase progress, sessions, findings, and supporting evidence for review. Vulnerabilities are deduplicated and stored in a structured management system, while configurable skills extend individual agents. The platform uses a React frontend, FastAPI backend, PostgreSQL database, and Docker-based deployment. -
8
Hiring Agent
AI agent to evaluate and score resumes
...The system can enrich that resume data with GitHub profile and repository signals when a profile is available. After the data is collected, it produces an explainable evaluation with category scores, supporting evidence, bonus points, and deductions. It can run locally with Ollama or use Google Gemini, which makes it flexible for teams that want either private local processing or hosted model access. -
9
PokeeResearch-7B
Pokee Deep Research Model Open Source Repo
PokeeResearchOSS provides an open-source, agentic “deep research” model centered on a 7B backbone that can browse, read, and synthesize current information from the web. Instead of relying only on static training data, the agent performs searches, visits pages, and extracts evidence before forming answers to complex queries. It is built to operate end-to-end: planning a research strategy, gathering sources, reasoning over conflicting claims, and writing a grounded response. The repository includes evaluation results on multi-step QA and research benchmarks, illustrating how web-time context boosts accuracy. ... -
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.
-
10
Oh My Hermes
All in one plugin for Hermes Agent
Oh My Hermes is an operating layer for Hermes Agent that adds structured routing, coding workflows, long-term memory, and evidence-aware execution. It keeps Hermes as the conversational front end while deciding which workflow, model category, and specialist capability should handle each task. Work can be split into parallel lanes with isolated worktrees and typed completion states. The plugin includes a reviewed memory system that stores approved records with provenance and aging rules. ... -
11
Cangjie Skill
Distill high-value content like books, long videos, podcasts, and more
...Each accepted skill records supporting material, a reconstructed explanation, examples, trigger situations, executable steps, and limitations. Strict verification rejects generic or weak ideas that lack independent evidence, predictive value, or meaningful uniqueness. The generated package can include an overview, glossary, reference graph, long-form digest, individual skill files, and test prompts. Completed skills can be installed for compatible coding agents such as Claude Code and Cursor. -
12
MiroThinker
MiroThinker is an open source deep research agent
...Rather than simply generating responses from a single prompt, the agent performs structured multi-step reasoning processes that involve searching for information, analyzing evidence, and synthesizing conclusions. The platform is optimized for research tasks such as financial forecasting, knowledge discovery, and large-scale information synthesis. MiroThinker has been evaluated on several agent benchmarks and has demonstrated strong performance on tests designed to measure deep research capabilities. -
13
Sprix SAGE Router
State-aware SELF/COLLABORATE/HANDOFF routing for A2A agent networks
...The system assigns remaining requirements to agents through task dependency graphs and estimates execution schedules. It learns contextual reliability and outcome information from previous execution evidence instead of relying on a single reputation score. Bounded search and replanning allow the router to compare feasible teams and revise decisions as task conditions change. -
14
Harness Engineering
Field guide, and agent context bundle for harness engineering
...It treats the model and agent as fixed while strengthening the surrounding context, tools, constraints, and proof mechanisms. The repository organizes developed arguments, practical cases, source evidence, evaluations, and reusable playbooks into distinct layers. Its agent guide routes each task to the smallest relevant set of materials instead of loading the entire corpus. The playbooks help teams improve one representative workflow, review repository readiness, and compare changes over time. The project emphasizes reliability, security, maintainability, compatibility, authority, and cumulative organizational learning. ... -
15
Deep Search Agent
Implement a concise and clear Deep Search Agent from 0
...The repository illustrates how large language models can be orchestrated with tools and planning logic to execute complex search workflows rather than single-prompt responses. It typically combines reasoning, retrieval, and iterative refinement so the agent can break down questions, gather evidence, and synthesize structured outputs. The project is positioned primarily as a proof of concept for deep research agents rather than a production-ready system. Its architecture highlights agent loops, tool calling, and stepwise execution, which are increasingly important patterns in modern AI automation. Overall, the demo serves as a practical reference for developers exploring autonomous research agents and multi-tool LLM orchestration. -
16
...Vulnerability + Evidence + Reproducibility + Proof / PoC + Impact ================ Validated Finding
- Previous
- You're on page 1
- Next
