simplicio-loop 3.43.12__tar.gz → 3.43.16__tar.gz

simplicio_loop-3.43.16/PKG-INFO

@@ -0,0 +1,95 @@
+Metadata-Version: 2.4
+Name: simplicio-loop
+Version: 3.43.16
+Summary: Standalone orchestrator for mapper and simplicio-dev-cli. No Runtime.
+Author-email: Wesley Simplicio <wesleybob4@gmail.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/simpletibr/simplicio-loop
+Project-URL: Repository, https://github.com/simpletibr/simplicio-loop
+Project-URL: Issues, https://github.com/simpletibr/simplicio-loop/issues
+Keywords: ai,agent,orchestrator,llm,claude,cursor,automation,ralph-loop,token-economy,cli
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Build Tools
+Classifier: Topic :: Utilities
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: simplicio-cli<0.19,>=0.18.16
+Requires-Dist: simplicio-mapper<0.27,>=0.26.34
+Requires-Dist: tiktoken<1,>=0.12.0
+Provides-Extra: dev
+Requires-Dist: setuptools>=77; extra == "dev"
+Requires-Dist: pytest>=7; extra == "dev"
+Requires-Dist: pytest-cov>=4; extra == "dev"
+Requires-Dist: cryptography<50,>=42; extra == "dev"
+Requires-Dist: jsonschema<5,>=4; extra == "dev"
+Provides-Extra: ml
+Requires-Dist: model2vec>=0.3; extra == "ml"
+Requires-Dist: numpy>=1.21; extra == "ml"
+Provides-Extra: uvloop
+Requires-Dist: uvloop>=0.19; platform_system != "Windows" and extra == "uvloop"
+Dynamic: license-file
+
+# simplicio-loop
+
+**The Universal Looping AI Orchestrator** — a runtime-agnostic **super-plugin** (7 skills) that
+drains any queue of work end-to-end on **any LLM / runtime**:
+`discover → implement → verify → merge → close → watch 24/7`, behind safety gates and evidence
+checks, at up to **96% fewer tokens**. Not a chatbot. A worker.
+
+![simplicio-loop](https://raw.githubusercontent.com/wesleysimplicio/simplicio-loop/main/assets/simplicio-loop-hero-2026.png)
+
+## Install
+
+```bash
+pip install simplicio-loop
+```
+
+Then drop the skills + hooks into your project (or globally):
+
+```bash
+simplicio-loop install            # into ./.claude of the current project
+simplicio-loop install --global   # into ~/.claude (all projects)
+```
+
+Now invoke it from your agent runtime (Claude Code, Cursor, Codex, Gemini, …):
+
+```
+/simplicio-loop finish all the open issues
+```
+
+## What you get — 7 skills
+
+| Skill | What it does |
+|---|---|
+| `simplicio-loop` | Unified public entrypoint: orchestrator core + hardened loop behind one command. |
+| `simplicio-tasks` | Legacy alias kept only for compatibility with older installs and saved prompts. |
+| `simplicio-orient` | Terminal-first token economy — output-reduction catalog, tee-cache, signatures-read. |
+| `simplicio-review` | Adversarial review — parallel subagents on distinct rubrics, deduped into one verdict. |
+| `simplicio-compress` | Output + memory compression, byte-preserving identifiers. |
+| `simplicio-autoresearch` | Evolutionary mutate/eval/keep-revert optimizer — yool-guardrailed caps, git-isolated branch, anti-Goodhart gate-first eval. |
+| `simplicio-learn` | Retrospective — durable, deduped lessons written back to memory. |
+
+## Highlights
+
+- **12 runtimes, one protocol** — Claude Code, Codex, VS Code/Copilot, Cursor, Antigravity, Kiro,
+  OpenCode, Gemini, Aider, Simplicio Agent (formerly Hermes), OpenClaw, Orca.
+- **Evidence-gated completion** — never a false "done"; exits only on a verified `<promise>`,
+  cap, spindle handoff, or STOP.
+- **Token economy** — honest "answer concisely" baseline; savings credited only on verified-correct
+  outcomes.
+
+Requires Python 3.11+. The Loop dependency closure includes `simplicio-mapper`
+and `simplicio-cli`; Python 3.11 is
+therefore the honest minimum for an installed bundle. The package remains
+pure cross-platform Python.
+
+MIT — part of the [Simplicio](https://github.com/wesleysimplicio) ecosystem.
+Full docs: <https://github.com/wesleysimplicio/simplicio-loop>

simplicio_loop-3.43.16/PYPI.md

@@ -0,0 +1,56 @@
+# simplicio-loop
+
+**The Universal Looping AI Orchestrator** — a runtime-agnostic **super-plugin** (7 skills) that
+drains any queue of work end-to-end on **any LLM / runtime**:
+`discover → implement → verify → merge → close → watch 24/7`, behind safety gates and evidence
+checks, at up to **96% fewer tokens**. Not a chatbot. A worker.
+
+![simplicio-loop](https://raw.githubusercontent.com/wesleysimplicio/simplicio-loop/main/assets/simplicio-loop-hero-2026.png)
+
+## Install
+
+```bash
+pip install simplicio-loop
+```
+
+Then drop the skills + hooks into your project (or globally):
+
+```bash
+simplicio-loop install            # into ./.claude of the current project
+simplicio-loop install --global   # into ~/.claude (all projects)
+```
+
+Now invoke it from your agent runtime (Claude Code, Cursor, Codex, Gemini, …):
+
+```
+/simplicio-loop finish all the open issues
+```
+
+## What you get — 7 skills
+
+| Skill | What it does |
+|---|---|
+| `simplicio-loop` | Unified public entrypoint: orchestrator core + hardened loop behind one command. |
+| `simplicio-tasks` | Legacy alias kept only for compatibility with older installs and saved prompts. |
+| `simplicio-orient` | Terminal-first token economy — output-reduction catalog, tee-cache, signatures-read. |
+| `simplicio-review` | Adversarial review — parallel subagents on distinct rubrics, deduped into one verdict. |
+| `simplicio-compress` | Output + memory compression, byte-preserving identifiers. |
+| `simplicio-autoresearch` | Evolutionary mutate/eval/keep-revert optimizer — yool-guardrailed caps, git-isolated branch, anti-Goodhart gate-first eval. |
+| `simplicio-learn` | Retrospective — durable, deduped lessons written back to memory. |
+
+## Highlights
+
+- **12 runtimes, one protocol** — Claude Code, Codex, VS Code/Copilot, Cursor, Antigravity, Kiro,
+  OpenCode, Gemini, Aider, Simplicio Agent (formerly Hermes), OpenClaw, Orca.
+- **Evidence-gated completion** — never a false "done"; exits only on a verified `<promise>`,
+  cap, spindle handoff, or STOP.
+- **Token economy** — honest "answer concisely" baseline; savings credited only on verified-correct
+  outcomes.
+
+Requires Python 3.11+. The Loop dependency closure includes `simplicio-mapper`
+and `simplicio-cli`; Python 3.11 is
+therefore the honest minimum for an installed bundle. The package remains
+pure cross-platform Python.
+
+MIT — part of the [Simplicio](https://github.com/wesleysimplicio) ecosystem.
+Full docs: <https://github.com/wesleysimplicio/simplicio-loop>