AutomationSoftware development

goal-forge

Turn a rough coding idea into a measurable contract for long Codex runs.

AutomationSoftware development

goal-forge

Turn a rough coding idea into a measurable contract for long Codex runs.

AutomationSoftware developmentCodex

codex-autoresearch

@leo-lilinxiaoPython

Drive Codex toward measurable code goals while reverting failed experiments automatically.

Project overview

Use Codex Autoresearch when a repository task has a numeric outcome, such as fewer test failures, better coverage, lower latency, or a smaller binary. The skill confirms the target, editable scope, metric command, regression guard, and run mode, then lets Codex try one focused change per iteration. Improvements are committed and retained; failed or regressive trials are reverted through Git, with an auditable event history. It can run interactively or in the background, but each experiment requires a clean named Git branch and sufficient access to create and revert commits.

Stars: 1,982
Forks: 117
License: MIT

AutomationSoftware developmentClaude Code

paper2code

@PrathamLearnsToCodePython

Turn an arXiv paper into cited code with explicit uncertainty notes.

Stars: 1,447
Forks: 173
License: MIT

AutomationSoftware developmentClaude Code

agent-sandbox-skill

@dislerPython

Run agent code, builds, hosting, and browser tests inside isolated E2B sandboxes.

Project overview

Agent Sandbox Skill gives Claude Code, Codex, and Gemini CLI managed E2B environments for engineering work that should not touch the local filesystem or production systems. Agents can install dependencies, run untrusted code, scaffold and build full-stack applications, expose a hosted port, and perform Playwright-based visual checks. Commands cover small sandbox tasks as well as plan, build, host, and test workflows, with lifecycle tools that preserve a sandbox across turns. An E2B API key is required, and compute and hosted previews depend on the E2B service.

Stars: 377
Forks: 96
License: Not declared

AutomationSoftware developmentClaude Code

recall-loom

@Frappucc1noPython

Preserve project context, decisions, and next steps across AI coding sessions.

Project overview

RecallLoom adds a file-based memory layer to long-running AI work, storing project background, current progress, key decisions, and next steps in Markdown and JSON beside the project. When users switch sessions, models, or coding tools, a new agent can restore the controlled current state before continuing, record progress, and check whether continuity files are missing, stale, or conflicting. It is deliberately focused on project continuity, not repository-wide knowledge retrieval, task orchestration, or autonomous execution.

Stars: 147
Forks: 4
License: Apache-2.0

goal-forge

goal-forge

Project overview

Repository facts

Related projects

codex-autoresearch

paper2code

agent-sandbox-skill

recall-loom