Reverify

Hyperresearch is an MIT-licensed Python command-line research harness that extends Claude Code with an agent-driven, persistent research knowledge base. It classifies a query into light, full, or opt-in dissertation work and runs a tier-adaptive pipeline covering query decomposition, source search and fetching, contradiction and locus analysis, depth investigation, evidence digestion, multi-angle drafting, synthesis, adversarial criticism, targeted gap fetching, surgical patching, citation checks, and readability review. The pipeline stores fetched sources as Markdown notes with a rebuildable SQLite index, provenance links, lifecycle statuses, full-text or optional semantic search, source-quality and retraction metadata, and resumable per-run manifests. It can fetch PDFs, seek disclosed open-access replacements for thin or blocked academic sources through Unpaywall and Europe PMC, and apply structural checks for citation bindings, quote integrity, provenance, retractions, and patch-only editing. The vault can also be accessed through an MCP server or a dependency-free local web UI. It is installed with pip for Python 3.11–3.13 and is intended to run with Claude Code; model assignments and research scale can be configured per project.

OrcaReplay is an open-source replay and debugging tool for AI-agent executions, built by the OrcaRouter.ai team. It records an agent run as a local trace, including model requests and responses, tool calls and results, shell exit codes and timing, filesystem snapshots, MCP traffic, and selected network activity. It runs as a local proxy and capture layer around an unmodified agent. A proxy records model traffic, while PATH shims, JSON-RPC interception, filesystem snapshots, fetch hooks, and optional TLS interception capture effects that model transcripts cannot show. The resulting timeline can be viewed, exported, queried through JSON or MCP, and analyzed with recorded versus inferred causal edges. The same recorded stream supports offline replay with the network blocked, forking from a derived checkpoint onto another model, and comparison of several models with an optional verification command. Replay uses the recorded conversation and workspace state; interactive terminal sessions can be approximate because prompts and interactive-only tools may not exist on the wire. The CLI is installed with npm, requires Node 20 or newer, stores runs under `.orca/runs/`, and the code, CLI, viewer, adapters, and trace format implementation are released under Apache-2.0; the trace specification is CC BY 4.0. Traces are local and redacted on write, but the project describes them as sensitive and treats redaction as best-effort.

An AI software-development agent from Replit that builds, modifies, publishes, and deploys applications from natural-language prompts. It can generate user interfaces and databases, implement application workflows such as electronic signing and checkout, connect custom domains, and manage deployment.

Reef is open-source continual-learning infrastructure for self-improving AI agents, developed by Human-Agent-Society. It connects agent inference, interaction records, feedback, learning jobs, evaluation, and versioned delivery, supporting updates to model weights as well as agent harnesses such as prompts, rules, and skills. Each learning cycle has four stages: Reef serves requests and records interactions; matches later scores or structured feedback to those records; produces a candidate update from eligible records; and evaluates the candidate against a configured selection policy before publishing it. Rejected candidates leave the previous release serving, while accepted updates are committed and delivered without restarting the service. The project provides an HTTP API with OpenAI- and Anthropic-compatible inference endpoints, feedback reporting, scenario-based releases, and integrations for training or inference components including Slime and SGLang. It can be installed from PyPI as `reef-infra` or from source; artifact and checkpoint management requires Git LFS.

Reverse Skill is an open-source, client-neutral cybersecurity skills router for AI coding agents performing reverse engineering, authorized penetration testing, security research, and CTF work. It processes a task through structured routing rules and a primary master-routing workflow, initializes authorization and network scope before action, selects a scenario-specific skill, checks available tools, MCP servers, and scripts, and records a timeline, evidence-to-finding path, report, and field journal rather than relying on guessed commands. Supported scenarios include APK and mobile analysis, binary and .NET reverse engineering, frontend JavaScript and encrypted-parameter analysis, DSL-VM reverse engineering, HTTP capture and request replay, malware and YARA analysis, penetration testing, attack-chain orchestration, case review, CTFs, firmware and IoT security, patch-diff analysis, exploit development, EDR bypass research, API and GraphQL security, supply-chain and SBOM security, and LLM security. Its documented tool ecosystem includes JADX, Apktool, Frida, IDA Pro, radare2, Ghidra, BurpSuite, and YARA. The repository provides platform-specific setup and tool-index refresh scripts for Windows, Linux, macOS, and Kali Linux, with prerequisites including a JDK, Node.js, and Python. It supports Claude Code, Codex, Cursor, OpenCode, and other compatible clients while keeping client adapters separate from the routing core, and includes cross-platform CI, routing regression tests, structure and supply-chain checks, and generated skill-navigation indexes.