memla 0.1.0__tar.gz

memla-0.1.0/PKG-INFO

@@ -0,0 +1,171 @@
+Metadata-Version: 2.4
+Name: memla
+Version: 0.1.0
+Summary: Memla CLI for bounded coding and math runtimes.
+Author-email: Jackfarmer2328 <samatarsalahudeen@gmail.com>
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+Requires-Dist: requests<3,>=2.31
+Requires-Dist: torch>=2.1
+Requires-Dist: transformers>=4.40
+Requires-Dist: peft>=0.7
+Requires-Dist: safetensors>=0.4
+Requires-Dist: sentence-transformers>=2.2
+Requires-Dist: fastapi>=0.100
+Requires-Dist: uvicorn>=0.20
+Requires-Dist: fastmcp>=2.0
+Requires-Dist: bitsandbytes>=0.41
+Requires-Dist: accelerate>=0.25
+Requires-Dist: sympy>=1.12
+
+# Memla CLI
+
+Memla is a bounded runtime that helps smaller local models make better technical decisions inside verifier-backed loops.
+
+This public repo is the CLI-first version of Memla:
+- local coding workflow planning and execution
+- coding benchmarks for patch execution and compile/backtest loops
+- bounded math benchmarks for decision-layer proof
+- a small proof packet showing the current strongest results
+
+It is intentionally narrower than the internal research repo.
+
+## What is here
+
+- `memla.py`
+  - top-level CLI entry point
+- `memory_system/`
+  - the runtime, coding session, patch benchmark, compile benchmark, math benchmark, and pack builders
+- `cases/`
+  - small bundled case files for quick benchmark runs
+- `proof/`
+  - the current proof packet and key benchmark artifacts
+- `tests/`
+  - focused tests for the coding, math, and CLI surfaces
+
+## Current claim
+
+The current public proof packet is in:
+- `proof/current_pack/`
+
+Current strongest bounded claim:
+- on coding, `qwen3.5:9b + Memla` beat local `qwen2.5:32b` raw on execution outcome in the OAuth patch benchmark
+- on math, `qwen3.5:4b + Memla` matched `qwen2.5:32b` raw on the bounded harder pack
+- on ambiguous math decision states, Memla lifted both `4b` and `9b` to perfect choice accuracy on the tested slice
+
+This is not a claim of universal model parity. It is a claim about bounded runtimes with verifiers.
+
+## Quick start
+
+Prerequisites:
+- Python 3.11+
+- Ollama running locally
+- one or more local models already pulled
+
+Install:
+
+```bash
+py -3 -m pip install .
+```
+
+Smoke-check the CLI:
+
+```bash
+memla --help
+```
+
+Run a local environment check:
+
+```bash
+memla doctor --repo-root . --model qwen3.5:9b
+```
+
+## Main commands
+
+Build a workflow plan inside a repo:
+
+```bash
+memla coding plan --prompt "Fix the auth regression" --repo-root .
+```
+
+Run a bounded coding turn with optional verification:
+
+```bash
+memla coding run --prompt "Repair the failing auth tests" --repo-root . --test-command "pytest -q"
+```
+
+Run the patch execution benchmark:
+
+```bash
+memla coding benchmark-patch --pack path\\to\\git_history_case_pack.json --raw-model qwen2.5:32b --memla-model qwen3.5:9b
+```
+
+Run the compile-loop benchmark:
+
+```bash
+memla coding benchmark-compile --cases cases\\coding_eval_cases.jsonl --repo-root . --model qwen3.5:9b
+```
+
+Run the bounded math benchmark:
+
+```bash
+memla math benchmark --cases cases\\math_linear_c2a_v2_harder.jsonl --teacher-model qwen2.5:32b --student-models qwen3.5:4b qwen3.5:9b --executor-mode stepwise_rerank --teacher-trace-source hybrid
+```
+
+Rebuild the proof packet:
+
+```bash
+memla pack thesis --coding proof\\current_pack\\frozen\\coding_patch_execution_report.json --math-rerank proof\\current_pack\\frozen\\math_step_rerank_report.json --math-progress proof\\current_pack\\frozen\\math_progress_report.json
+```
+
+Benchmark commands write report bundles under `./memla_reports/` by default.
+
+Publish the current proof pack to the repo root for Vercel:
+
+```bash
+memla pack publish-site --source proof\\current_pack --out-dir .
+```
+
+## Proof artifacts
+
+Main public proof packet:
+- `proof/current_pack/`
+
+Supporting reports:
+- `proof/reports/coding_oauth_patch/`
+- `proof/reports/coding_fastapi_patch/`
+- `proof/reports/coding_fastapi_compile/`
+- `proof/reports/math_qwen32b_rerank/`
+- `proof/reports/math_qwen32b_stepwise/`
+
+## Tests
+
+Focused verification:
+
+```bash
+py -3 -m pytest -q tests\\test_step13_coding_compile_loop.py tests\\test_step14_compile_loop_benchmark.py tests\\test_step15_patch_execution_benchmark.py tests\\test_step16_math_c2a_benchmark.py tests\\test_step17_memla_cli.py
+```
+
+## Product direction
+
+Memla is being packaged as:
+- a local/private coding runtime for smaller models
+- a CLI first, not a chat app first
+- a verifier-backed system, not a prompt wrapper
+
+The wedge is simple:
+
+**make local 9b/14b/32b coding models more execution-capable than their raw form.**
+
+## GitHub and Vercel
+
+This repo is set up so GitHub and Vercel can work together cleanly:
+- GitHub Actions runs the focused CLI/benchmark test suite on push and pull request
+- `memla pack publish-site --source proof\\current_pack --out-dir .` syncs the current proof pack to the repo root
+- the root `vercel.json` is written as a static deployment config so Vercel can deploy the proof site directly from the repo root
+
+Practical flow:
+1. update proof artifacts
+2. run `memla pack publish-site`
+3. push to GitHub
+4. let Vercel redeploy from the latest commit

memla-0.1.0/README.md

@@ -0,0 +1,151 @@
+# Memla CLI
+
+Memla is a bounded runtime that helps smaller local models make better technical decisions inside verifier-backed loops.
+
+This public repo is the CLI-first version of Memla:
+- local coding workflow planning and execution
+- coding benchmarks for patch execution and compile/backtest loops
+- bounded math benchmarks for decision-layer proof
+- a small proof packet showing the current strongest results
+
+It is intentionally narrower than the internal research repo.
+
+## What is here
+
+- `memla.py`
+  - top-level CLI entry point
+- `memory_system/`
+  - the runtime, coding session, patch benchmark, compile benchmark, math benchmark, and pack builders
+- `cases/`
+  - small bundled case files for quick benchmark runs
+- `proof/`
+  - the current proof packet and key benchmark artifacts
+- `tests/`
+  - focused tests for the coding, math, and CLI surfaces
+
+## Current claim
+
+The current public proof packet is in:
+- `proof/current_pack/`
+
+Current strongest bounded claim:
+- on coding, `qwen3.5:9b + Memla` beat local `qwen2.5:32b` raw on execution outcome in the OAuth patch benchmark
+- on math, `qwen3.5:4b + Memla` matched `qwen2.5:32b` raw on the bounded harder pack
+- on ambiguous math decision states, Memla lifted both `4b` and `9b` to perfect choice accuracy on the tested slice
+
+This is not a claim of universal model parity. It is a claim about bounded runtimes with verifiers.
+
+## Quick start
+
+Prerequisites:
+- Python 3.11+
+- Ollama running locally
+- one or more local models already pulled
+
+Install:
+
+```bash
+py -3 -m pip install .
+```
+
+Smoke-check the CLI:
+
+```bash
+memla --help
+```
+
+Run a local environment check:
+
+```bash
+memla doctor --repo-root . --model qwen3.5:9b
+```
+
+## Main commands
+
+Build a workflow plan inside a repo:
+
+```bash
+memla coding plan --prompt "Fix the auth regression" --repo-root .
+```
+
+Run a bounded coding turn with optional verification:
+
+```bash
+memla coding run --prompt "Repair the failing auth tests" --repo-root . --test-command "pytest -q"
+```
+
+Run the patch execution benchmark:
+
+```bash
+memla coding benchmark-patch --pack path\\to\\git_history_case_pack.json --raw-model qwen2.5:32b --memla-model qwen3.5:9b
+```
+
+Run the compile-loop benchmark:
+
+```bash
+memla coding benchmark-compile --cases cases\\coding_eval_cases.jsonl --repo-root . --model qwen3.5:9b
+```
+
+Run the bounded math benchmark:
+
+```bash
+memla math benchmark --cases cases\\math_linear_c2a_v2_harder.jsonl --teacher-model qwen2.5:32b --student-models qwen3.5:4b qwen3.5:9b --executor-mode stepwise_rerank --teacher-trace-source hybrid
+```
+
+Rebuild the proof packet:
+
+```bash
+memla pack thesis --coding proof\\current_pack\\frozen\\coding_patch_execution_report.json --math-rerank proof\\current_pack\\frozen\\math_step_rerank_report.json --math-progress proof\\current_pack\\frozen\\math_progress_report.json
+```
+
+Benchmark commands write report bundles under `./memla_reports/` by default.
+
+Publish the current proof pack to the repo root for Vercel:
+
+```bash
+memla pack publish-site --source proof\\current_pack --out-dir .
+```
+
+## Proof artifacts
+
+Main public proof packet:
+- `proof/current_pack/`
+
+Supporting reports:
+- `proof/reports/coding_oauth_patch/`
+- `proof/reports/coding_fastapi_patch/`
+- `proof/reports/coding_fastapi_compile/`
+- `proof/reports/math_qwen32b_rerank/`
+- `proof/reports/math_qwen32b_stepwise/`
+
+## Tests
+
+Focused verification:
+
+```bash
+py -3 -m pytest -q tests\\test_step13_coding_compile_loop.py tests\\test_step14_compile_loop_benchmark.py tests\\test_step15_patch_execution_benchmark.py tests\\test_step16_math_c2a_benchmark.py tests\\test_step17_memla_cli.py
+```
+
+## Product direction
+
+Memla is being packaged as:
+- a local/private coding runtime for smaller models
+- a CLI first, not a chat app first
+- a verifier-backed system, not a prompt wrapper
+
+The wedge is simple:
+
+**make local 9b/14b/32b coding models more execution-capable than their raw form.**
+
+## GitHub and Vercel
+
+This repo is set up so GitHub and Vercel can work together cleanly:
+- GitHub Actions runs the focused CLI/benchmark test suite on push and pull request
+- `memla pack publish-site --source proof\\current_pack --out-dir .` syncs the current proof pack to the repo root
+- the root `vercel.json` is written as a static deployment config so Vercel can deploy the proof site directly from the repo root
+
+Practical flow:
+1. update proof artifacts
+2. run `memla pack publish-site`
+3. push to GitHub
+4. let Vercel redeploy from the latest commit

memla-0.1.0/memla.egg-info/PKG-INFO

@@ -0,0 +1,171 @@
+Metadata-Version: 2.4
+Name: memla
+Version: 0.1.0
+Summary: Memla CLI for bounded coding and math runtimes.
+Author-email: Jackfarmer2328 <samatarsalahudeen@gmail.com>
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+Requires-Dist: requests<3,>=2.31
+Requires-Dist: torch>=2.1
+Requires-Dist: transformers>=4.40
+Requires-Dist: peft>=0.7
+Requires-Dist: safetensors>=0.4
+Requires-Dist: sentence-transformers>=2.2
+Requires-Dist: fastapi>=0.100
+Requires-Dist: uvicorn>=0.20
+Requires-Dist: fastmcp>=2.0
+Requires-Dist: bitsandbytes>=0.41
+Requires-Dist: accelerate>=0.25
+Requires-Dist: sympy>=1.12
+
+# Memla CLI
+
+Memla is a bounded runtime that helps smaller local models make better technical decisions inside verifier-backed loops.
+
+This public repo is the CLI-first version of Memla:
+- local coding workflow planning and execution
+- coding benchmarks for patch execution and compile/backtest loops
+- bounded math benchmarks for decision-layer proof
+- a small proof packet showing the current strongest results
+
+It is intentionally narrower than the internal research repo.
+
+## What is here
+
+- `memla.py`
+  - top-level CLI entry point
+- `memory_system/`
+  - the runtime, coding session, patch benchmark, compile benchmark, math benchmark, and pack builders
+- `cases/`
+  - small bundled case files for quick benchmark runs
+- `proof/`
+  - the current proof packet and key benchmark artifacts
+- `tests/`
+  - focused tests for the coding, math, and CLI surfaces
+
+## Current claim
+
+The current public proof packet is in:
+- `proof/current_pack/`
+
+Current strongest bounded claim:
+- on coding, `qwen3.5:9b + Memla` beat local `qwen2.5:32b` raw on execution outcome in the OAuth patch benchmark
+- on math, `qwen3.5:4b + Memla` matched `qwen2.5:32b` raw on the bounded harder pack
+- on ambiguous math decision states, Memla lifted both `4b` and `9b` to perfect choice accuracy on the tested slice
+
+This is not a claim of universal model parity. It is a claim about bounded runtimes with verifiers.
+
+## Quick start
+
+Prerequisites:
+- Python 3.11+
+- Ollama running locally
+- one or more local models already pulled
+
+Install:
+
+```bash
+py -3 -m pip install .
+```
+
+Smoke-check the CLI:
+
+```bash
+memla --help
+```
+
+Run a local environment check:
+
+```bash
+memla doctor --repo-root . --model qwen3.5:9b
+```
+
+## Main commands
+
+Build a workflow plan inside a repo:
+
+```bash
+memla coding plan --prompt "Fix the auth regression" --repo-root .
+```
+
+Run a bounded coding turn with optional verification:
+
+```bash
+memla coding run --prompt "Repair the failing auth tests" --repo-root . --test-command "pytest -q"
+```
+
+Run the patch execution benchmark:
+
+```bash
+memla coding benchmark-patch --pack path\\to\\git_history_case_pack.json --raw-model qwen2.5:32b --memla-model qwen3.5:9b
+```
+
+Run the compile-loop benchmark:
+
+```bash
+memla coding benchmark-compile --cases cases\\coding_eval_cases.jsonl --repo-root . --model qwen3.5:9b
+```
+
+Run the bounded math benchmark:
+
+```bash
+memla math benchmark --cases cases\\math_linear_c2a_v2_harder.jsonl --teacher-model qwen2.5:32b --student-models qwen3.5:4b qwen3.5:9b --executor-mode stepwise_rerank --teacher-trace-source hybrid
+```
+
+Rebuild the proof packet:
+
+```bash
+memla pack thesis --coding proof\\current_pack\\frozen\\coding_patch_execution_report.json --math-rerank proof\\current_pack\\frozen\\math_step_rerank_report.json --math-progress proof\\current_pack\\frozen\\math_progress_report.json
+```
+
+Benchmark commands write report bundles under `./memla_reports/` by default.
+
+Publish the current proof pack to the repo root for Vercel:
+
+```bash
+memla pack publish-site --source proof\\current_pack --out-dir .
+```
+
+## Proof artifacts
+
+Main public proof packet:
+- `proof/current_pack/`
+
+Supporting reports:
+- `proof/reports/coding_oauth_patch/`
+- `proof/reports/coding_fastapi_patch/`
+- `proof/reports/coding_fastapi_compile/`
+- `proof/reports/math_qwen32b_rerank/`
+- `proof/reports/math_qwen32b_stepwise/`
+
+## Tests
+
+Focused verification:
+
+```bash
+py -3 -m pytest -q tests\\test_step13_coding_compile_loop.py tests\\test_step14_compile_loop_benchmark.py tests\\test_step15_patch_execution_benchmark.py tests\\test_step16_math_c2a_benchmark.py tests\\test_step17_memla_cli.py
+```
+
+## Product direction
+
+Memla is being packaged as:
+- a local/private coding runtime for smaller models
+- a CLI first, not a chat app first
+- a verifier-backed system, not a prompt wrapper
+
+The wedge is simple:
+
+**make local 9b/14b/32b coding models more execution-capable than their raw form.**
+
+## GitHub and Vercel
+
+This repo is set up so GitHub and Vercel can work together cleanly:
+- GitHub Actions runs the focused CLI/benchmark test suite on push and pull request
+- `memla pack publish-site --source proof\\current_pack --out-dir .` syncs the current proof pack to the repo root
+- the root `vercel.json` is written as a static deployment config so Vercel can deploy the proof site directly from the repo root
+
+Practical flow:
+1. update proof artifacts
+2. run `memla pack publish-site`
+3. push to GitHub
+4. let Vercel redeploy from the latest commit

memla-0.1.0/memla.egg-info/SOURCES.txt

@@ -0,0 +1,62 @@
+README.md
+pyproject.toml
+memla.egg-info/PKG-INFO
+memla.egg-info/SOURCES.txt
+memla.egg-info/dependency_links.txt
+memla.egg-info/entry_points.txt
+memla.egg-info/requires.txt
+memla.egg-info/top_level.txt
+memory_system/__init__.py
+memory_system/cli.py
+memory_system/main.py
+memory_system/ollama_client.py
+memory_system/sync.py
+memory_system/adapters/__init__.py
+memory_system/adapters/ewc.py
+memory_system/adapters/gradient_pass.py
+memory_system/adapters/lora_manager.py
+memory_system/adapters/merge.py
+memory_system/distillation/__init__.py
+memory_system/distillation/abstract_c2a_benchmark.py
+memory_system/distillation/acquisition_pack_builder.py
+memory_system/distillation/batch_runner.py
+memory_system/distillation/coding_compile_loop.py
+memory_system/distillation/coding_log.py
+memory_system/distillation/coding_proxy.py
+memory_system/distillation/comparison_runner.py
+memory_system/distillation/compile_loop_benchmark.py
+memory_system/distillation/constraint_graph.py
+memory_system/distillation/demo_runner.py
+memory_system/distillation/diligence_packet_builder.py
+memory_system/distillation/eval_harness.py
+memory_system/distillation/exporter.py
+memory_system/distillation/git_history_cases.py
+memory_system/distillation/hypothesis_benchmark.py
+memory_system/distillation/math_c2a_benchmark.py
+memory_system/distillation/patch_execution_benchmark.py
+memory_system/distillation/pitch_pack_builder.py
+memory_system/distillation/seed_runner.py
+memory_system/distillation/thesis_pack_builder.py
+memory_system/distillation/transfer_eval.py
+memory_system/distillation/workflow_planner.py
+memory_system/distillation/workspace_capture.py
+memory_system/memory/__init__.py
+memory_system/memory/chunk_manager.py
+memory_system/memory/consolidator.py
+memory_system/memory/episode_log.py
+memory_system/memory/lazy_import.py
+memory_system/memory/llm_extractor.py
+memory_system/middleware/__init__.py
+memory_system/middleware/context_builder.py
+memory_system/middleware/quality.py
+memory_system/middleware/ttt_layer.py
+memory_system/projection/__init__.py
+memory_system/projection/gradient_filter.py
+memory_system/reasoning/__init__.py
+memory_system/reasoning/trajectory.py
+tests/test_ollama_client.py
+tests/test_step13_coding_compile_loop.py
+tests/test_step14_compile_loop_benchmark.py
+tests/test_step15_patch_execution_benchmark.py
+tests/test_step16_math_c2a_benchmark.py
+tests/test_step17_memla_cli.py

memla-0.1.0/memla.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

memla-0.1.0/memla.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+memla = memory_system.cli:main

memla-0.1.0/memla.egg-info/requires.txt

@@ -0,0 +1,12 @@
+requests<3,>=2.31
+torch>=2.1
+transformers>=4.40
+peft>=0.7
+safetensors>=0.4
+sentence-transformers>=2.2
+fastapi>=0.100
+uvicorn>=0.20
+fastmcp>=2.0
+bitsandbytes>=0.41
+accelerate>=0.25
+sympy>=1.12

memla-0.1.0/memla.egg-info/top_level.txt

@@ -0,0 +1 @@
+memory_system

memla-0.1.0/memory_system/__init__.py

@@ -0,0 +1,2 @@
+__all__ = []
+

memla-0.1.0/memory_system/adapters/__init__.py

@@ -0,0 +1,7 @@
+"""
+Step 2+ modules live here (LoRA, EWC, merge).
+Not implemented in Step 1.
+"""
+
+__all__ = []
+