longmem 0.1.0__tar.gz

longmem-0.1.0/.gitignore

@@ -0,0 +1,40 @@
+# Python
+__pycache__/
+*.py[cod]
+*.pyo
+*.pyd
+.Python
+*.egg-info/
+*.egg
+.eggs/
+
+# Build
+dist/
+build/
+.hatch/
+
+# Virtual environments
+.venv/
+venv/
+env/
+
+# uv
+.uv/
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+
+# OS
+.DS_Store
+Thumbs.db
+
+# longmem-cursor DB (local data, never commit)
+.longmem-cursor/

longmem-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Mariia Eremina
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

longmem-0.1.0/PKG-INFO

@@ -0,0 +1,243 @@
+Metadata-Version: 2.4
+Name: longmem
+Version: 0.1.0
+Summary: Persistent cross-project memory for Cursor and Claude Code — stores problem/solution pairs with semantic search
+Project-URL: Homepage, https://github.com/marerem/longmem
+Project-URL: Bug Tracker, https://github.com/marerem/longmem/issues
+License: MIT
+License-File: LICENSE
+Keywords: claude-code,cursor,embeddings,lancedb,llm,mcp,memory,ollama,rag
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.11
+Requires-Dist: fastmcp<4,>=3.2.4
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: lancedb>=0.17.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: pyarrow>=14.0.0
+Provides-Extra: openai
+Requires-Dist: openai>=1.0.0; extra == 'openai'
+Description-Content-Type: text/markdown
+
+<div align="center">
+
+<img src="longmem_github_logo.svg" alt="longmem" width="480"/>
+
+**Cross-project memory for AI coding assistants.**  
+Stop solving the same problems twice.
+
+[![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org)
+[![License: MIT](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
+[![Tests](https://github.com/marerem/longmem/actions/workflows/test.yml/badge.svg)](https://github.com/marerem/longmem/actions)
+[![Coverage](https://codecov.io/gh/marerem/longmem/branch/main/graph/badge.svg)](https://codecov.io/gh/marerem/longmem)
+[![Open Issues](https://img.shields.io/github/issues/marerem/longmem)](https://github.com/marerem/longmem/issues)
+[![Closed Issues](https://img.shields.io/github/issues-closed/marerem/longmem?color=green)](https://github.com/marerem/longmem/issues?q=is%3Aissue+is%3Aclosed)
+
+</div>
+
+---
+
+Your AI solves the same bug in a different project six months later. Writes the same boilerplate. Explains the same pattern. You already knew the answer.
+
+**longmem** gives your AI a persistent memory that works across every project and every session. Before reasoning from scratch, it searches what you've already solved. After something works, it saves it. The longer you use it, the less you repeat yourself.
+
+```
+You describe a problem
+        │
+        ▼
+  search_similar()   ──── match found (≥85%) ────▶  cached solution + edge cases
+        │
+    no match
+        │
+        ▼
+  AI reasons from scratch
+        │
+   "it works"
+        │
+        ▼
+  confirm_solution()  ──── saved for every future project
+```
+
+---
+
+## Why longmem
+
+| | longmem | others |
+|---|---|---|
+| **Cost** | Free — local [Ollama](https://ollama.com) embeddings | Requires API calls per session |
+| **Privacy** | Nothing leaves your machine | Sends observations to external APIs |
+| **Process** | Starts on demand, no daemon | Background worker + open port required |
+| **IDE support** | Cursor + Claude Code | Primarily one IDE |
+| **Search** | Hybrid: semantic + keyword (FTS5) | Vector-only or keyword-only |
+| **Teams** | Export / import / shared DB path / S3 | Single-user |
+| **License** | MIT | AGPL / proprietary |
+
+---
+
+## Quickstart
+
+**1. Install**
+
+```bash
+pipx install longmem
+```
+
+**2. Setup** — checks Ollama, pulls the embedding model, writes your IDE config
+
+```bash
+longmem init
+```
+
+**3. Activate in each project** — copies the rules file that tells the AI how to use memory
+
+```bash
+cd your-project
+longmem install
+```
+
+**4. Restart your IDE.** Memory tools are now active on every chat.
+
+> **Need Ollama?** Install from [ollama.com](https://ollama.com), then `ollama pull nomic-embed-text`. Or use OpenAI — see [Configuration](#configuration).
+
+---
+
+## How it works
+
+longmem is an [MCP](https://modelcontextprotocol.io) server. Your IDE starts it on demand. Two rules drive the workflow:
+
+**Rule 1 — search first.** Before the AI reasons about any bug or question, it calls `search_similar`. If a match is found (cosine similarity ≥ 85%), the cached solution is returned with any edge-case notes. Below the threshold, the AI solves normally.
+
+**Rule 2 — save on success.** When you confirm something works, the AI calls `confirm_solution`. One parameter — just the solution text. Problem metadata is auto-filled from the earlier search.
+
+The rules file (`longmem.mdc` for Cursor, `CLAUDE.md` for Claude Code) wires this up automatically. No manual prompting.
+
+**AI forgot to save?** Run `longmem review` — an interactive CLI to save any solution in 30 seconds.
+
+---
+
+## CLI
+
+| Command | What it does |
+|---------|-------------|
+| `longmem init` | One-time setup: Ollama check, model pull, writes IDE config |
+| `longmem install` | Copy rules into the current project |
+| `longmem status` | Config, Ollama reachability, entry count, DB size |
+| `longmem export [file]` | Dump all entries to JSON — backup or share |
+| `longmem import <file>` | Load a JSON export — onboard teammates or migrate machines |
+| `longmem review` | Manually save a solution when the AI forgot |
+
+`longmem` with no arguments starts the MCP server (used by your IDE).
+
+---
+
+## Configuration
+
+Config lives at `~/.longmem/config.toml`. All fields are optional — defaults work with a local Ollama instance.
+
+### Switch to OpenAI embeddings
+
+```toml
+embedder       = "openai"
+openai_model   = "text-embedding-3-small"
+openai_api_key = "sk-..."   # or set OPENAI_API_KEY
+```
+
+Install the extra: `pip install 'longmem[openai]'`
+
+### Team shared database
+
+Point every team member's config at the same path:
+
+```toml
+# NFS / shared drive
+db_path = "/mnt/shared/longmem/db"
+```
+
+Or use cloud storage:
+
+```toml
+# S3 (uses AWS env vars)
+db_uri = "s3://my-bucket/longmem"
+
+# LanceDB Cloud
+db_uri = "db://my-org/my-db"
+lancedb_api_key = "ldb_..."   # or set LANCEDB_API_KEY
+```
+
+No shared mount? Use `longmem export` / `longmem import` to distribute a snapshot.
+
+### Tuning
+
+```toml
+similarity_threshold = 0.85   # minimum score to surface a cached result (default 0.85)
+duplicate_threshold  = 0.95   # minimum score to block a save as a near-duplicate (default 0.95)
+```
+
+---
+
+## MCP tools
+
+The server exposes 11 tools. The two you interact with most:
+
+- **`search_similar`** — semantic + keyword hybrid search. Returns ranked matches with similarity scores, edge cases, and a `keyword_match` flag when the hit came from exact text rather than vector similarity.
+- **`confirm_solution`** — saves a solution with one parameter. Problem metadata auto-filled from the preceding search.
+
+Full list: `save_solution`, `correct_solution`, `enrich_solution`, `add_edge_case`, `search_by_project`, `delete_solution`, `rebuild_index`, `list_recent`, `stats`.
+
+Call `rebuild_index` once you reach 256+ entries to compact the database and build the ANN index for faster search.
+
+---
+
+## Category reference
+
+Categories pre-filter before vector search — keeps retrieval fast at any scale.
+
+| Category | Use for |
+|---|---|
+| `ci_cd` | GitHub Actions, Jenkins, GitLab CI, build failures |
+| `containers` | Docker, Kubernetes, Helm, OOM kills |
+| `infrastructure` | Terraform, Pulumi, CDK, IaC drift |
+| `cloud` | AWS/GCP/Azure SDK, IAM, quota errors |
+| `networking` | DNS, TLS, load balancers, timeouts, proxies |
+| `observability` | Logging, metrics, tracing, Prometheus, Grafana |
+| `auth_security` | OAuth, JWT, RBAC, secrets, CVEs |
+| `data_pipeline` | Airflow, Prefect, Dagster, ETL, data quality |
+| `ml_training` | GPU/CUDA, distributed training, OOM |
+| `model_serving` | vLLM, Triton, inference latency, batching |
+| `experiment_tracking` | MLflow, W&B, DVC, reproducibility |
+| `llm_rag` | Chunking, embedding, retrieval, reranking |
+| `llm_api` | Rate limits, token cost, prompt engineering |
+| `vector_db` | Pinecone, Weaviate, Qdrant, LanceDB |
+| `agents` | LangChain, LlamaIndex, tool-calling, agent memory |
+| `database` | SQL/NoSQL, migrations, slow queries |
+| `api` | REST, GraphQL, gRPC, versioning |
+| `async_concurrency` | Race conditions, event loops, deadlocks |
+| `dependencies` | Version conflicts, packaging, lock files |
+| `performance` | Profiling, memory leaks, caching |
+| `testing` | Flaky tests, mocks, integration vs unit |
+| `architecture` | Design patterns, service boundaries, refactoring |
+| `other` | When nothing above fits |
+
+---
+
+## Contributing
+
+```bash
+git clone https://github.com/mariia-eremina/longmem
+cd longmem
+uv sync --group dev
+uv run pytest
+```
+
+Pull requests welcome — bug fixes, features, docs, tests.
+
+---
+
+## License
+
+MIT — see [LICENSE](LICENSE).

longmem-0.1.0/README.md

@@ -0,0 +1,217 @@
+<div align="center">
+
+<img src="longmem_github_logo.svg" alt="longmem" width="480"/>
+
+**Cross-project memory for AI coding assistants.**  
+Stop solving the same problems twice.
+
+[![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org)
+[![License: MIT](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
+[![Tests](https://github.com/marerem/longmem/actions/workflows/test.yml/badge.svg)](https://github.com/marerem/longmem/actions)
+[![Coverage](https://codecov.io/gh/marerem/longmem/branch/main/graph/badge.svg)](https://codecov.io/gh/marerem/longmem)
+[![Open Issues](https://img.shields.io/github/issues/marerem/longmem)](https://github.com/marerem/longmem/issues)
+[![Closed Issues](https://img.shields.io/github/issues-closed/marerem/longmem?color=green)](https://github.com/marerem/longmem/issues?q=is%3Aissue+is%3Aclosed)
+
+</div>
+
+---
+
+Your AI solves the same bug in a different project six months later. Writes the same boilerplate. Explains the same pattern. You already knew the answer.
+
+**longmem** gives your AI a persistent memory that works across every project and every session. Before reasoning from scratch, it searches what you've already solved. After something works, it saves it. The longer you use it, the less you repeat yourself.
+
+```
+You describe a problem
+        │
+        ▼
+  search_similar()   ──── match found (≥85%) ────▶  cached solution + edge cases
+        │
+    no match
+        │
+        ▼
+  AI reasons from scratch
+        │
+   "it works"
+        │
+        ▼
+  confirm_solution()  ──── saved for every future project
+```
+
+---
+
+## Why longmem
+
+| | longmem | others |
+|---|---|---|
+| **Cost** | Free — local [Ollama](https://ollama.com) embeddings | Requires API calls per session |
+| **Privacy** | Nothing leaves your machine | Sends observations to external APIs |
+| **Process** | Starts on demand, no daemon | Background worker + open port required |
+| **IDE support** | Cursor + Claude Code | Primarily one IDE |
+| **Search** | Hybrid: semantic + keyword (FTS5) | Vector-only or keyword-only |
+| **Teams** | Export / import / shared DB path / S3 | Single-user |
+| **License** | MIT | AGPL / proprietary |
+
+---
+
+## Quickstart
+
+**1. Install**
+
+```bash
+pipx install longmem
+```
+
+**2. Setup** — checks Ollama, pulls the embedding model, writes your IDE config
+
+```bash
+longmem init
+```
+
+**3. Activate in each project** — copies the rules file that tells the AI how to use memory
+
+```bash
+cd your-project
+longmem install
+```
+
+**4. Restart your IDE.** Memory tools are now active on every chat.
+
+> **Need Ollama?** Install from [ollama.com](https://ollama.com), then `ollama pull nomic-embed-text`. Or use OpenAI — see [Configuration](#configuration).
+
+---
+
+## How it works
+
+longmem is an [MCP](https://modelcontextprotocol.io) server. Your IDE starts it on demand. Two rules drive the workflow:
+
+**Rule 1 — search first.** Before the AI reasons about any bug or question, it calls `search_similar`. If a match is found (cosine similarity ≥ 85%), the cached solution is returned with any edge-case notes. Below the threshold, the AI solves normally.
+
+**Rule 2 — save on success.** When you confirm something works, the AI calls `confirm_solution`. One parameter — just the solution text. Problem metadata is auto-filled from the earlier search.
+
+The rules file (`longmem.mdc` for Cursor, `CLAUDE.md` for Claude Code) wires this up automatically. No manual prompting.
+
+**AI forgot to save?** Run `longmem review` — an interactive CLI to save any solution in 30 seconds.
+
+---
+
+## CLI
+
+| Command | What it does |
+|---------|-------------|
+| `longmem init` | One-time setup: Ollama check, model pull, writes IDE config |
+| `longmem install` | Copy rules into the current project |
+| `longmem status` | Config, Ollama reachability, entry count, DB size |
+| `longmem export [file]` | Dump all entries to JSON — backup or share |
+| `longmem import <file>` | Load a JSON export — onboard teammates or migrate machines |
+| `longmem review` | Manually save a solution when the AI forgot |
+
+`longmem` with no arguments starts the MCP server (used by your IDE).
+
+---
+
+## Configuration
+
+Config lives at `~/.longmem/config.toml`. All fields are optional — defaults work with a local Ollama instance.
+
+### Switch to OpenAI embeddings
+
+```toml
+embedder       = "openai"
+openai_model   = "text-embedding-3-small"
+openai_api_key = "sk-..."   # or set OPENAI_API_KEY
+```
+
+Install the extra: `pip install 'longmem[openai]'`
+
+### Team shared database
+
+Point every team member's config at the same path:
+
+```toml
+# NFS / shared drive
+db_path = "/mnt/shared/longmem/db"
+```
+
+Or use cloud storage:
+
+```toml
+# S3 (uses AWS env vars)
+db_uri = "s3://my-bucket/longmem"
+
+# LanceDB Cloud
+db_uri = "db://my-org/my-db"
+lancedb_api_key = "ldb_..."   # or set LANCEDB_API_KEY
+```
+
+No shared mount? Use `longmem export` / `longmem import` to distribute a snapshot.
+
+### Tuning
+
+```toml
+similarity_threshold = 0.85   # minimum score to surface a cached result (default 0.85)
+duplicate_threshold  = 0.95   # minimum score to block a save as a near-duplicate (default 0.95)
+```
+
+---
+
+## MCP tools
+
+The server exposes 11 tools. The two you interact with most:
+
+- **`search_similar`** — semantic + keyword hybrid search. Returns ranked matches with similarity scores, edge cases, and a `keyword_match` flag when the hit came from exact text rather than vector similarity.
+- **`confirm_solution`** — saves a solution with one parameter. Problem metadata auto-filled from the preceding search.
+
+Full list: `save_solution`, `correct_solution`, `enrich_solution`, `add_edge_case`, `search_by_project`, `delete_solution`, `rebuild_index`, `list_recent`, `stats`.
+
+Call `rebuild_index` once you reach 256+ entries to compact the database and build the ANN index for faster search.
+
+---
+
+## Category reference
+
+Categories pre-filter before vector search — keeps retrieval fast at any scale.
+
+| Category | Use for |
+|---|---|
+| `ci_cd` | GitHub Actions, Jenkins, GitLab CI, build failures |
+| `containers` | Docker, Kubernetes, Helm, OOM kills |
+| `infrastructure` | Terraform, Pulumi, CDK, IaC drift |
+| `cloud` | AWS/GCP/Azure SDK, IAM, quota errors |
+| `networking` | DNS, TLS, load balancers, timeouts, proxies |
+| `observability` | Logging, metrics, tracing, Prometheus, Grafana |
+| `auth_security` | OAuth, JWT, RBAC, secrets, CVEs |
+| `data_pipeline` | Airflow, Prefect, Dagster, ETL, data quality |
+| `ml_training` | GPU/CUDA, distributed training, OOM |
+| `model_serving` | vLLM, Triton, inference latency, batching |
+| `experiment_tracking` | MLflow, W&B, DVC, reproducibility |
+| `llm_rag` | Chunking, embedding, retrieval, reranking |
+| `llm_api` | Rate limits, token cost, prompt engineering |
+| `vector_db` | Pinecone, Weaviate, Qdrant, LanceDB |
+| `agents` | LangChain, LlamaIndex, tool-calling, agent memory |
+| `database` | SQL/NoSQL, migrations, slow queries |
+| `api` | REST, GraphQL, gRPC, versioning |
+| `async_concurrency` | Race conditions, event loops, deadlocks |
+| `dependencies` | Version conflicts, packaging, lock files |
+| `performance` | Profiling, memory leaks, caching |
+| `testing` | Flaky tests, mocks, integration vs unit |
+| `architecture` | Design patterns, service boundaries, refactoring |
+| `other` | When nothing above fits |
+
+---
+
+## Contributing
+
+```bash
+git clone https://github.com/mariia-eremina/longmem
+cd longmem
+uv sync --group dev
+uv run pytest
+```
+
+Pull requests welcome — bug fixes, features, docs, tests.
+
+---
+
+## License
+
+MIT — see [LICENSE](LICENSE).

longmem-0.1.0/pyproject.toml

@@ -0,0 +1,60 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "longmem"
+version = "0.1.0"
+description = "Persistent cross-project memory for Cursor and Claude Code — stores problem/solution pairs with semantic search"
+readme = "README.md"
+requires-python = ">=3.11"
+license = { text = "MIT" }
+keywords = ["cursor", "claude-code", "mcp", "memory", "llm", "rag", "embeddings", "lancedb", "ollama"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+    "fastmcp>=3.2.4,<4",
+    "lancedb>=0.17.0",
+    "pyarrow>=14.0.0",
+    "httpx>=0.27.0",
+    "numpy>=1.24.0",
+]
+
+[project.optional-dependencies]
+openai = ["openai>=1.0.0"]
+
+[project.urls]
+"Homepage" = "https://github.com/marerem/longmem"
+"Bug Tracker" = "https://github.com/marerem/longmem/issues"
+
+[project.scripts]
+longmem = "longmem.cli:main"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/longmem"]
+
+# Ensure non-Python template files are included in the wheel
+[tool.hatch.build.targets.wheel.shared-data]
+
+[tool.hatch.build]
+include = [
+    "src/longmem/**",
+]
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["tests"]
+
+[dependency-groups]
+dev = [
+    "pytest>=9.0.3",
+    "pytest-asyncio>=1.3.0",
+    "pytest-cov>=5.0.0",
+]

longmem-0.1.0/src/longmem/__init__.py

@@ -0,0 +1,3 @@
+"""longmem-cursor: persistent memory MCP server for Cursor IDE."""
+
+__version__ = "0.1.0"