Gentleman-Programming/engram

Persistent memory for AI coding agents
Agent-agnostic. Single binary. Zero dependencies.

Installation • Agent Setup • Architecture • Plugins • Contributing • Full Docs

Your AI coding agent forgets everything when the session ends. Engram gives it a brain. A **Go binary** with SQLite + FTS5 full-text search, exposed via CLI, HTTP API, MCP server, and an interactive TUI. Works with **any agent** that supports MCP — Claude Code, OpenCode, Gemini CLI, Codex, VS Code (Copilot), Antigravity, Cursor, Windsurf, or anything else. ``` Agent (Claude Code / OpenCode / Gemini CLI / Codex / VS Code / Antigravity / ...) ↓ MCP stdio Engram (single Go binary) ↓ SQLite + FTS5 (~/.engram/engram.db) ``` ## 快速开始 ### 安装 ``` brew install gentleman-programming/tap/engram ``` Windows, Linux, and other install methods → [docs/INSTALLATION.md](docs/INSTALLATION.md) ### 设置您的代理 | Agent | One-liner | |-------|-----------| | Claude Code | `claude plugin marketplace add Gentleman-Programming/engram && claude plugin install engram` | | OpenCode | `engram setup opencode` | | Gemini CLI | `engram setup gemini-cli` | | Codex | `engram setup codex` | | VS Code | `code --add-mcp '{"name":"engram","command":"engram","args":["mcp"]}'` | | Cursor / Windsurf / Any MCP | See [docs/AGENT-SETUP.md](docs/AGENT-SETUP.md) | Full per-agent config, Memory Protocol, and compaction survival → [docs/AGENT-SETUP.md](docs/AGENT-SETUP.md) That's it. No Node.js, no Python, no Docker. **One binary, one SQLite file.** ## 工作原理 ``` 1. Agent completes significant work (bugfix, architecture decision, etc.) 2. Agent calls mem_save → title, type, What/Why/Where/Learned 3. Engram persists to SQLite with FTS5 indexing 4. Next session: agent searches memory, gets relevant context ``` Full details on session lifecycle, topic keys, and memory hygiene → [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) ## MCP 工具 (15) | Category | Tools | |----------|-------| | **Save & Update** | `mem_save`, `mem_update`, `mem_delete`, `mem_suggest_topic_key` | | **Search & Retrieve** | `mem_search`, `mem_context`, `mem_timeline`, `mem_get_observation` | | **Session Lifecycle** | `mem_session_start`, `mem_session_end`, `mem_session_summary` | | **Utilities** | `mem_save_prompt`, `mem_stats`, `mem_capture_passive`, `mem_merge_projects` | Full tool reference with parameters → [DOCS.md#mcp-tools-15-tools](DOCS.md#mcp-tools-15-tools) ## 终端用户界面 ``` engram tui ```

**Navigation**: `j/k` vim keys, `Enter` to drill in, `/` to search, `Esc` back. Catppuccin Mocha theme. ## Git 同步 Share memories across machines. Uses compressed chunks — no merge conflicts, no huge files. ``` engram sync # Export new memories as compressed chunk git add .engram/ && git commit -m "sync engram memories" engram sync --import # On another machine: import new chunks engram sync --status # Check sync status ``` Full sync documentation → [DOCS.md](DOCS.md) ## CLI 参考 | Command | Description | |---------|-------------| | `engram setup [agent]` | Install agent integration | | `engram serve [port]` | Start HTTP API (default: 7437) | | `engram mcp` | Start MCP server (stdio) | | `engram tui` | Launch terminal UI | | `engram search ` | Search memories | | `engram save