palinode 0.7.0__tar.gz

palinode-0.7.0/PKG-INFO

@@ -0,0 +1,309 @@
+Metadata-Version: 2.4
+Name: palinode
+Version: 0.7.0
+Summary: The memory substrate for AI agents and developer tools. Git-versioned, file-native, MCP-first.
+Author-email: Paul Kyle <paul@phasespace.co>
+License: MIT
+Project-URL: Homepage, https://github.com/phasespace-labs/palinode
+Project-URL: Documentation, https://github.com/phasespace-labs/palinode/tree/main/docs
+Project-URL: Repository, https://github.com/phasespace-labs/palinode
+Project-URL: Issues, https://github.com/phasespace-labs/palinode/issues
+Project-URL: Changelog, https://github.com/phasespace-labs/palinode/blob/main/docs/CHANGELOG.md
+Keywords: ai,agents,memory,mcp,llm,rag,knowledge-management
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+Requires-Dist: sqlite-vec
+Requires-Dist: watchdog
+Requires-Dist: pyyaml
+Requires-Dist: httpx
+Requires-Dist: python-frontmatter
+Requires-Dist: fastapi
+Requires-Dist: uvicorn
+Requires-Dist: pydantic
+Requires-Dist: mcp
+Requires-Dist: rich
+Requires-Dist: click
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-asyncio; extra == "dev"
+
+# Palinode
+
+**Persistent memory for AI agents. Markdown in, markdown out, git everything.**
+
+Your agent's memory is a folder of markdown files. Palinode indexes them with hybrid search, compacts them with an LLM, and exposes them through any interface you want — MCP, REST API, CLI, or plugin hooks. If every service crashes, `cat` still works.
+
+*A palinode is a poem that retracts what was said before and says it better. That's what memory compaction does.*
+
+---
+
+## The Idea
+
+Most agent memory is a black box. You can't read it, you can't diff it, you can't `grep` it when the vector DB is down. Palinode bets on **plain files as the source of truth** and builds everything else as a derived index.
+
+```
+Files (markdown + YAML frontmatter)
+  ↓ watched
+Index (SQLite-vec vectors + FTS5 keywords, single .db file)
+  ↓ queried by
+Interfaces (MCP server, REST API, CLI, plugin hooks)
+  ↓ compacted by
+LLM (proposes ops → deterministic executor applies them → git commits)
+```
+
+That's the whole architecture. One directory of `.md` files, one SQLite database, one API server. No Postgres, no Redis, no cloud dependency.
+
+---
+
+## One Backend, Every Interface
+
+Palinode doesn't care how you talk to it. The same 17 tools work everywhere:
+
+| Interface | Transport | Best For |
+|-----------|-----------|----------|
+| **MCP Server** | Streamable HTTP or stdio | Claude Code, Claude Desktop, Cursor, Zed |
+| **REST API** | HTTP on :6340 | Scripts, webhooks, custom integrations |
+| **CLI** | Wraps REST API | Cron jobs, SSH, shell scripts (8x fewer tokens than MCP) |
+| **Plugin** | Agent lifecycle hooks | Agent frameworks with inject/extract patterns |
+
+Set up once on a server. Connect from any machine, any IDE, any agent framework. The MCP server is a pure HTTP client — it holds no state, no database connection, no embedder. Point it at the API and go.
+
+```json
+{
+  "mcpServers": {
+    "palinode": { "url": "http://your-server:6341/mcp/" }
+  }
+}
+```
+
+That's the entire client config for Claude Code, Claude Desktop, Cursor, or Zed. See [docs/MCP-SETUP.md](docs/MCP-SETUP.md) for multi-IDE setup, or [docs/INSTALL-CLAUDE-CODE.md](docs/INSTALL-CLAUDE-CODE.md) for Claude Code specifically.
+
+---
+
+## How It Works
+
+**Store** — Typed markdown files (people, projects, decisions, insights) with YAML frontmatter. Git-versioned. Human-readable. Editable in Obsidian, VS Code, vim, or anything.
+
+**Index** — A file watcher embeds with BGE-M3 and indexes with FTS5 as you save. Content-hash dedup skips re-embedding unchanged files (~90% savings). Single SQLite file, zero external services.
+
+**Search** — Hybrid BM25 + vector search merged with Reciprocal Rank Fusion. Keyword precision when you need exact terms, semantic recall when you don't. Optional associative entity graph and prospective triggers.
+
+**Compact** — Weekly consolidation where an LLM proposes structured operations (KEEP / UPDATE / MERGE / SUPERSEDE / ARCHIVE) and a deterministic executor applies them. The LLM never touches your files directly. Every compaction is a git commit you can review, blame, or revert.
+
+**Audit** — `git blame` any fact. `git diff` any change. `rollback` any mistake. These aren't just git-compatible files — `palinode_diff`, `palinode_blame`, and `palinode_rollback` are first-class tools your agent can call.
+
+---
+
+## Quick Start
+
+```bash
+# Install
+git clone https://github.com/phasespace-labs/palinode && cd palinode
+python3 -m venv venv && source venv/bin/activate
+pip install -e .
+
+# Create your memory directory
+mkdir -p ~/.palinode/{people,projects,decisions,insights,daily}
+cd ~/.palinode && git init
+cp /path/to/palinode/palinode.config.yaml.example palinode.config.yaml  # adjust path
+
+# Start services
+PALINODE_DIR=~/.palinode palinode-api        # REST API on :6340
+PALINODE_DIR=~/.palinode palinode-watcher     # auto-indexes on file save
+PALINODE_DIR=~/.palinode palinode-mcp-sse     # MCP server on :6341 (optional)
+
+# Verify
+curl http://localhost:6340/status
+```
+
+> Your memory directory is **private**. It contains personal data. Never make it public. The code repo contains zero memory files.
+
+---
+
+## Tools
+
+17 tools available through every interface:
+
+| Tool | What It Does |
+|------|-------------|
+| `search` | Hybrid BM25 + vector search with category filter |
+| `save` | Store a typed memory (person, decision, insight, project) |
+| `list` | Browse memory files by type, filter by core status |
+| `read` | Read the full content of a memory file |
+| `ingest` | Fetch a URL and save as research |
+| `status` | Health check — file counts, index stats, service status |
+| `history` | Git history with diff stats, rename tracking, and limit |
+| `entities` | Entity graph — cross-references between memories |
+| `consolidate` | Preview or run LLM-powered compaction |
+| `diff` | What changed in the last N days |
+| `blame` | Trace a fact back to the commit that recorded it |
+| `rollback` | Revert a file to a previous commit (safe, creates new commit) |
+| `push` | Sync memory to a remote git repo |
+| `trigger` | Prospective recall — auto-inject when a topic comes up |
+| `lint` | Health scan — orphans, stale files, missing fields |
+| `session_end` | Capture summary, decisions, and blockers at end of session |
+| `prompt` | List, show, or activate versioned LLM prompts |
+
+Every tool is accessible as `palinode_<name>` via MCP, `palinode <name>` via CLI, or `POST/GET /<name>` via the REST API.
+
+---
+
+## Stack
+
+| Layer | Choice | Why |
+|-------|--------|-----|
+| Source of truth | Markdown + YAML frontmatter | Human-readable, git-versioned, portable |
+| Vector index | SQLite-vec (embedded) | No server, single file, zero config |
+| Keyword index | SQLite FTS5 (embedded) | BM25 for exact terms, zero dependencies |
+| Embeddings | BGE-M3 via Ollama | Local, private, no API key needed |
+| API | FastAPI | Lightweight, async, one process |
+| MCP | Python MCP SDK (Streamable HTTP) | Works with every IDE over the network |
+| CLI | Click (wraps REST API) | Shell-native, TTY-aware output |
+| Behavior | [`PROGRAM.md`](PROGRAM.md) | What to remember, how to extract, how to compact — edit one file to change all behavior |
+
+---
+
+## Memory File Format
+
+```yaml
+---
+id: project-palinode
+category: project
+name: Palinode
+core: true
+status: active
+entities: [person/paul]
+last_updated: 2026-04-05T00:00:00Z
+summary: "Persistent memory for AI agents."
+---
+# Palinode
+
+Your content here. As detailed or brief as you want.
+Files marked `core: true` are always in context.
+Everything else is retrieved on demand via hybrid search.
+```
+
+Open your memory directory as an [Obsidian](https://obsidian.md) vault for visual browsing. See [docs/OBSIDIAN-SETUP.md](docs/OBSIDIAN-SETUP.md).
+
+---
+
+## Configuration
+
+All behavior is in `palinode.config.yaml`:
+
+```yaml
+memory_dir: "~/.palinode"
+ollama_url: "http://localhost:11434"
+embedding_model: "bge-m3"
+
+recall:
+  search:
+    top_k: 5
+    threshold: 0.4
+  core:
+    max_chars_per_file: 3000
+
+search:
+  hybrid_enabled: true
+  hybrid_weight: 0.5         # 0.0 = vector only, 1.0 = BM25 only
+
+consolidation:
+  llm_model: "llama3.1:8b"   # any chat model that outputs JSON
+  llm_url: "http://localhost:11434"
+  llm_fallbacks:              # tried in order if primary fails
+    - model: "qwen2.5:14b-instruct"
+      url: "http://localhost:11434"
+```
+
+All models are swappable. Any Ollama embedding model, any OpenAI-compatible chat endpoint. See [palinode.config.yaml.example](palinode.config.yaml.example) for the full reference.
+
+---
+
+## Requirements
+
+- **Python 3.11+**
+- **Ollama** with `bge-m3` (`ollama pull bge-m3`)
+- **Git**
+
+Optional: a chat model for consolidation (any 7B+ works).
+
+---
+
+## API Reference
+
+| Method | Path | Description |
+|--------|------|-------------|
+| `GET` | `/status` | Health check + stats |
+| `POST` | `/search` | Hybrid search with filters |
+| `POST` | `/search-associative` | Entity graph traversal |
+| `POST` | `/save` | Create a typed memory file |
+| `POST` | `/ingest-url` | Fetch URL, save as research |
+| `GET/POST` | `/triggers` | Prospective recall triggers |
+| `POST` | `/consolidate` | Run or preview compaction |
+| `GET` | `/list` | Browse files by type |
+| `GET` | `/read?file_path=...` | Read a memory file |
+| `GET` | `/history/{file_path}` | Git log for a file |
+| `GET` | `/diff` | Recent changes |
+| `GET` | `/blame/{file_path}` | Git blame |
+| `POST` | `/rollback` | Revert a file |
+| `POST` | `/push` | Push to git remote |
+| `POST` | `/reindex` | Rebuild indices |
+| `POST` | `/session-end` | Capture session summary |
+| `POST` | `/lint` | Health scan |
+
+---
+
+## Design Principles
+
+1. **Files are truth.** Not databases, not vector stores. Markdown files that humans can read, edit, and version with git.
+
+2. **Typed, not flat.** People, projects, decisions, insights — each has structure. This enables reliable retrieval and consolidation.
+
+3. **Consolidation, not accumulation.** 100 sessions should produce 20 well-maintained files, not 100 unread dumps.
+
+4. **Invisible when working.** The human talks to their agent. Palinode works behind the scenes.
+
+5. **Graceful degradation.** Vector index down? Read files directly. Embedding service down? Grep. Machine off? It's a git repo, clone it anywhere.
+
+6. **Zero taxonomy burden.** The system classifies. The human reviews. If the human has to maintain a taxonomy, the system dies.
+
+---
+
+## What's Unique
+
+- **Git operations as agent tools** — `diff`, `blame`, `rollback`, `push` exposed via MCP. No other system makes git ops callable by the agent.
+- **Operation-based compaction** — KEEP/UPDATE/MERGE/SUPERSEDE/ARCHIVE DSL. LLM proposes, deterministic executor disposes. Every compaction is a reviewable git commit.
+- **Per-fact addressability** — `<!-- fact:slug -->` IDs inline in markdown, invisible in rendering, preserved by git, targetable by compaction.
+- **4-phase injection** — Core (always) + Topic (per-turn search) + Associative (entity graph) + Triggered (prospective recall).
+- **Multi-transport MCP** — stdio for local, Streamable HTTP for remote. One server, any IDE on any machine.
+- **If everything crashes, `cat` still works.**
+
+---
+
+## Acknowledgments
+
+Palinode builds on ideas from [Karpathy's LLM Knowledge Bases](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f), [Letta](https://github.com/letta-ai/letta) (tiered memory), and [LangMem](https://github.com/langchain-ai/langmem) (typed schemas + background consolidation). See [docs/ACKNOWLEDGMENTS.md](docs/ACKNOWLEDGMENTS.md) for the full list.
+
+See also the [epistemic integrity discussion](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) in the Karpathy gist thread — particularly the problem of LLM wikis that "synthesise without citing, drift from sources without knowing it, and present false certainty where disagreement exists." Git-based provenance is Palinode's answer to that problem.
+
+If you know of prior art we missed, please [open an issue](https://github.com/phasespace-labs/palinode/issues).
+
+---
+
+## License
+
+MIT
+
+---
+
+*Built by [Paul Kyle](https://github.com/Paul-Kyle) with help from AI agents who use Palinode to remember building Palinode.*

palinode-0.7.0/README.md

@@ -0,0 +1,270 @@
+# Palinode
+
+**Persistent memory for AI agents. Markdown in, markdown out, git everything.**
+
+Your agent's memory is a folder of markdown files. Palinode indexes them with hybrid search, compacts them with an LLM, and exposes them through any interface you want — MCP, REST API, CLI, or plugin hooks. If every service crashes, `cat` still works.
+
+*A palinode is a poem that retracts what was said before and says it better. That's what memory compaction does.*
+
+---
+
+## The Idea
+
+Most agent memory is a black box. You can't read it, you can't diff it, you can't `grep` it when the vector DB is down. Palinode bets on **plain files as the source of truth** and builds everything else as a derived index.
+
+```
+Files (markdown + YAML frontmatter)
+  ↓ watched
+Index (SQLite-vec vectors + FTS5 keywords, single .db file)
+  ↓ queried by
+Interfaces (MCP server, REST API, CLI, plugin hooks)
+  ↓ compacted by
+LLM (proposes ops → deterministic executor applies them → git commits)
+```
+
+That's the whole architecture. One directory of `.md` files, one SQLite database, one API server. No Postgres, no Redis, no cloud dependency.
+
+---
+
+## One Backend, Every Interface
+
+Palinode doesn't care how you talk to it. The same 17 tools work everywhere:
+
+| Interface | Transport | Best For |
+|-----------|-----------|----------|
+| **MCP Server** | Streamable HTTP or stdio | Claude Code, Claude Desktop, Cursor, Zed |
+| **REST API** | HTTP on :6340 | Scripts, webhooks, custom integrations |
+| **CLI** | Wraps REST API | Cron jobs, SSH, shell scripts (8x fewer tokens than MCP) |
+| **Plugin** | Agent lifecycle hooks | Agent frameworks with inject/extract patterns |
+
+Set up once on a server. Connect from any machine, any IDE, any agent framework. The MCP server is a pure HTTP client — it holds no state, no database connection, no embedder. Point it at the API and go.
+
+```json
+{
+  "mcpServers": {
+    "palinode": { "url": "http://your-server:6341/mcp/" }
+  }
+}
+```
+
+That's the entire client config for Claude Code, Claude Desktop, Cursor, or Zed. See [docs/MCP-SETUP.md](docs/MCP-SETUP.md) for multi-IDE setup, or [docs/INSTALL-CLAUDE-CODE.md](docs/INSTALL-CLAUDE-CODE.md) for Claude Code specifically.
+
+---
+
+## How It Works
+
+**Store** — Typed markdown files (people, projects, decisions, insights) with YAML frontmatter. Git-versioned. Human-readable. Editable in Obsidian, VS Code, vim, or anything.
+
+**Index** — A file watcher embeds with BGE-M3 and indexes with FTS5 as you save. Content-hash dedup skips re-embedding unchanged files (~90% savings). Single SQLite file, zero external services.
+
+**Search** — Hybrid BM25 + vector search merged with Reciprocal Rank Fusion. Keyword precision when you need exact terms, semantic recall when you don't. Optional associative entity graph and prospective triggers.
+
+**Compact** — Weekly consolidation where an LLM proposes structured operations (KEEP / UPDATE / MERGE / SUPERSEDE / ARCHIVE) and a deterministic executor applies them. The LLM never touches your files directly. Every compaction is a git commit you can review, blame, or revert.
+
+**Audit** — `git blame` any fact. `git diff` any change. `rollback` any mistake. These aren't just git-compatible files — `palinode_diff`, `palinode_blame`, and `palinode_rollback` are first-class tools your agent can call.
+
+---
+
+## Quick Start
+
+```bash
+# Install
+git clone https://github.com/phasespace-labs/palinode && cd palinode
+python3 -m venv venv && source venv/bin/activate
+pip install -e .
+
+# Create your memory directory
+mkdir -p ~/.palinode/{people,projects,decisions,insights,daily}
+cd ~/.palinode && git init
+cp /path/to/palinode/palinode.config.yaml.example palinode.config.yaml  # adjust path
+
+# Start services
+PALINODE_DIR=~/.palinode palinode-api        # REST API on :6340
+PALINODE_DIR=~/.palinode palinode-watcher     # auto-indexes on file save
+PALINODE_DIR=~/.palinode palinode-mcp-sse     # MCP server on :6341 (optional)
+
+# Verify
+curl http://localhost:6340/status
+```
+
+> Your memory directory is **private**. It contains personal data. Never make it public. The code repo contains zero memory files.
+
+---
+
+## Tools
+
+17 tools available through every interface:
+
+| Tool | What It Does |
+|------|-------------|
+| `search` | Hybrid BM25 + vector search with category filter |
+| `save` | Store a typed memory (person, decision, insight, project) |
+| `list` | Browse memory files by type, filter by core status |
+| `read` | Read the full content of a memory file |
+| `ingest` | Fetch a URL and save as research |
+| `status` | Health check — file counts, index stats, service status |
+| `history` | Git history with diff stats, rename tracking, and limit |
+| `entities` | Entity graph — cross-references between memories |
+| `consolidate` | Preview or run LLM-powered compaction |
+| `diff` | What changed in the last N days |
+| `blame` | Trace a fact back to the commit that recorded it |
+| `rollback` | Revert a file to a previous commit (safe, creates new commit) |
+| `push` | Sync memory to a remote git repo |
+| `trigger` | Prospective recall — auto-inject when a topic comes up |
+| `lint` | Health scan — orphans, stale files, missing fields |
+| `session_end` | Capture summary, decisions, and blockers at end of session |
+| `prompt` | List, show, or activate versioned LLM prompts |
+
+Every tool is accessible as `palinode_<name>` via MCP, `palinode <name>` via CLI, or `POST/GET /<name>` via the REST API.
+
+---
+
+## Stack
+
+| Layer | Choice | Why |
+|-------|--------|-----|
+| Source of truth | Markdown + YAML frontmatter | Human-readable, git-versioned, portable |
+| Vector index | SQLite-vec (embedded) | No server, single file, zero config |
+| Keyword index | SQLite FTS5 (embedded) | BM25 for exact terms, zero dependencies |
+| Embeddings | BGE-M3 via Ollama | Local, private, no API key needed |
+| API | FastAPI | Lightweight, async, one process |
+| MCP | Python MCP SDK (Streamable HTTP) | Works with every IDE over the network |
+| CLI | Click (wraps REST API) | Shell-native, TTY-aware output |
+| Behavior | [`PROGRAM.md`](PROGRAM.md) | What to remember, how to extract, how to compact — edit one file to change all behavior |
+
+---
+
+## Memory File Format
+
+```yaml
+---
+id: project-palinode
+category: project
+name: Palinode
+core: true
+status: active
+entities: [person/paul]
+last_updated: 2026-04-05T00:00:00Z
+summary: "Persistent memory for AI agents."
+---
+# Palinode
+
+Your content here. As detailed or brief as you want.
+Files marked `core: true` are always in context.
+Everything else is retrieved on demand via hybrid search.
+```
+
+Open your memory directory as an [Obsidian](https://obsidian.md) vault for visual browsing. See [docs/OBSIDIAN-SETUP.md](docs/OBSIDIAN-SETUP.md).
+
+---
+
+## Configuration
+
+All behavior is in `palinode.config.yaml`:
+
+```yaml
+memory_dir: "~/.palinode"
+ollama_url: "http://localhost:11434"
+embedding_model: "bge-m3"
+
+recall:
+  search:
+    top_k: 5
+    threshold: 0.4
+  core:
+    max_chars_per_file: 3000
+
+search:
+  hybrid_enabled: true
+  hybrid_weight: 0.5         # 0.0 = vector only, 1.0 = BM25 only
+
+consolidation:
+  llm_model: "llama3.1:8b"   # any chat model that outputs JSON
+  llm_url: "http://localhost:11434"
+  llm_fallbacks:              # tried in order if primary fails
+    - model: "qwen2.5:14b-instruct"
+      url: "http://localhost:11434"
+```
+
+All models are swappable. Any Ollama embedding model, any OpenAI-compatible chat endpoint. See [palinode.config.yaml.example](palinode.config.yaml.example) for the full reference.
+
+---
+
+## Requirements
+
+- **Python 3.11+**
+- **Ollama** with `bge-m3` (`ollama pull bge-m3`)
+- **Git**
+
+Optional: a chat model for consolidation (any 7B+ works).
+
+---
+
+## API Reference
+
+| Method | Path | Description |
+|--------|------|-------------|
+| `GET` | `/status` | Health check + stats |
+| `POST` | `/search` | Hybrid search with filters |
+| `POST` | `/search-associative` | Entity graph traversal |
+| `POST` | `/save` | Create a typed memory file |
+| `POST` | `/ingest-url` | Fetch URL, save as research |
+| `GET/POST` | `/triggers` | Prospective recall triggers |
+| `POST` | `/consolidate` | Run or preview compaction |
+| `GET` | `/list` | Browse files by type |
+| `GET` | `/read?file_path=...` | Read a memory file |
+| `GET` | `/history/{file_path}` | Git log for a file |
+| `GET` | `/diff` | Recent changes |
+| `GET` | `/blame/{file_path}` | Git blame |
+| `POST` | `/rollback` | Revert a file |
+| `POST` | `/push` | Push to git remote |
+| `POST` | `/reindex` | Rebuild indices |
+| `POST` | `/session-end` | Capture session summary |
+| `POST` | `/lint` | Health scan |
+
+---
+
+## Design Principles
+
+1. **Files are truth.** Not databases, not vector stores. Markdown files that humans can read, edit, and version with git.
+
+2. **Typed, not flat.** People, projects, decisions, insights — each has structure. This enables reliable retrieval and consolidation.
+
+3. **Consolidation, not accumulation.** 100 sessions should produce 20 well-maintained files, not 100 unread dumps.
+
+4. **Invisible when working.** The human talks to their agent. Palinode works behind the scenes.
+
+5. **Graceful degradation.** Vector index down? Read files directly. Embedding service down? Grep. Machine off? It's a git repo, clone it anywhere.
+
+6. **Zero taxonomy burden.** The system classifies. The human reviews. If the human has to maintain a taxonomy, the system dies.
+
+---
+
+## What's Unique
+
+- **Git operations as agent tools** — `diff`, `blame`, `rollback`, `push` exposed via MCP. No other system makes git ops callable by the agent.
+- **Operation-based compaction** — KEEP/UPDATE/MERGE/SUPERSEDE/ARCHIVE DSL. LLM proposes, deterministic executor disposes. Every compaction is a reviewable git commit.
+- **Per-fact addressability** — `<!-- fact:slug -->` IDs inline in markdown, invisible in rendering, preserved by git, targetable by compaction.
+- **4-phase injection** — Core (always) + Topic (per-turn search) + Associative (entity graph) + Triggered (prospective recall).
+- **Multi-transport MCP** — stdio for local, Streamable HTTP for remote. One server, any IDE on any machine.
+- **If everything crashes, `cat` still works.**
+
+---
+
+## Acknowledgments
+
+Palinode builds on ideas from [Karpathy's LLM Knowledge Bases](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f), [Letta](https://github.com/letta-ai/letta) (tiered memory), and [LangMem](https://github.com/langchain-ai/langmem) (typed schemas + background consolidation). See [docs/ACKNOWLEDGMENTS.md](docs/ACKNOWLEDGMENTS.md) for the full list.
+
+See also the [epistemic integrity discussion](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) in the Karpathy gist thread — particularly the problem of LLM wikis that "synthesise without citing, drift from sources without knowing it, and present false certainty where disagreement exists." Git-based provenance is Palinode's answer to that problem.
+
+If you know of prior art we missed, please [open an issue](https://github.com/phasespace-labs/palinode/issues).
+
+---
+
+## License
+
+MIT
+
+---
+
+*Built by [Paul Kyle](https://github.com/Paul-Kyle) with help from AI agents who use Palinode to remember building Palinode.*

palinode-0.7.0/palinode/__init__.py

@@ -0,0 +1,14 @@
+"""
+Palinode — Persistent memory for AI agents.
+
+Files as truth. Vectors as search. Prompts as source code.
+
+Components:
+    core/       — Config, embeddings, storage, markdown parsing
+    api/        — FastAPI HTTP server
+    indexer/    — File watcher daemon (auto-indexes on save)
+    ingest/     — Ingestion pipeline (PDF, audio, URL, text)
+    mcp.py      — MCP server for Claude Code integration
+    cli.py      — Command-line interface
+"""
+__version__ = "0.2.0"