entroly
v1.0.88by juyterman1000 · author: Entroly
Automatic, evidence-bounded context activation and auditable context operations for AI coding agents.
What entroly does, in the publisher's words
Node/WASM package for Entroly, an auditable context engineering control plane for AI agents with local compression, recovery, receipts, and verification.
This package installs the current Node/WebAssembly Entroly runtime by depending on entroly-wasm, then exposes a short entroly binary that delegates to entroly-wasm. It is also the portable Codex plugin package: the hook, MCP manifest, launcher, and skill ship together with that local runtime dependency.
Restart Codex and trust the bundled hook. After the next task, inspect the activation evidence with entroly activation status. Raw prompt and session text are not stored in activation receipts.
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 2
- MCP servers
- 1
- Stars
- 483
- License
- Apache-2.0
- Repo created
- 2026-03-07
- Last pushed
- 2026-11-07
- Publisher type
- User
- Version
- 1.0.88
Links
Skills · 2
- entroly-agent-review
- entroly-evidence-operations
- Use Entroly for content-blind agent-history audits, explicit baseline/optimized trials, recoverable command or browser evidence, response contracts, and token-efficiency claim verification.
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
MCP servers · 1
- entrolystdio
- node ${PLUGIN_ROOT}/scripts/entroly-plugin-launch.mjs
- env vars: ENTROLY_NO_DOCKER · ENTROLY_MCP_PASSIVE · ENTROLY_MCP_PROFILE · ENTROLY_MAX_FILES
Read from the plugin's own mcp.json. We list environment variable names, never values.
Category
Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
context · coding-agents · receipts · verification · mcp
Related by publisher and keywords
Never reconstruct where you left off. Local-first continuity for you and your coding agents, resume, decisions, and what's still in the air. CLI, MCP, and Agent Skills for Cursor, Claude Code, Copilot, and Codex.
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
Reusable PowerContext skills and MCP configuration for agent integrations.
Cross-tool memory for AI agents through Nowledge Mem skills and MCP.
Find which dependency APIs your code uses changed after your coding model's training cutoff, and write short AGENTS.md notes from the API diff, each with its source.
Read repositories, edit code and run checks with wcode through local or remote MCP connections.
[](https://agentpluginsdirectory.com/plugins/entroly)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.