Усильте агента
Установка от издателя. Не эндпоинт PlugMCP.
Host a copy with our keys and logs.
В реестре пока нет пакетного релиза. Следуйте README репозитория.
Удалённый URL или команда на вашем компьютере? Чем различаются два способа установки
Запустить на PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
ЗапускОт издателя
You solved that bug last week. Your next agent session has no idea.
A local-first memory layer for CLI agents. indexes your Claude Code, Codex CLI, Cursor, Antigravity, and Pi session histories into a single SQLite + FTS5 database, then gives you one CLI/TUI to find old work by topic, repo, provider, or recency. It also ships an MCP server so your agent can search its own history.
Local-first memory layer for CLI agents. Indexes Claude Code, Codex CLI, Cursor, Antigravity, and Pi sessions into SQLite + FTS5, searchable from a CLI, TUI, or MCP server.
sessiongrepThe real payoff is portable context: your session history isn't trapped in one tool. Work you started in Claude Code can continue in Codex, and an agent can recover — and even critique — its own prior reasoning across every tool you use.
Read the announcement: Sessiongrep: a local-first memory layer for CLI agents.
Session transcripts already live on your machine — scattered across ~/.claude/projects, ~/.codex/sessions, ~/.cursor/projects as noisy JSONL with opaque filenames. The information is not missing, it's stranded. Humans don't want to read it; agents don't know how to retrieve it. Grep over JSONL drowns in tool payloads. Shell history captures commands but not reasoning. Cloud-synced or vector-backed alternatives bring secrets and URLs into systems that aren't yours.
sessiongrep keeps recall local. One static binary, one SQLite file, no daemon, no server. The index is a disposable cache — delete it and rebuild it whenever you want.
Provider adapters normalize Claude, Codex, Cursor, Antigravity, and Pi transcripts into a single Session model and write them into SQLite (WAL mode) with an FTS5 virtual table over transcript text, title, summary, and preview. Every read command runs an incremental reindex first — files whose mtime and size haven't changed are skipped, so search and list stay fast even as your history grows.
Only the conversation is indexed: your prompts and the agent's replies. Tool calls and their output, injected context (AGENTS.md, skill bodies, system reminders), and sub-agent transcripts are left out, so a hit points at what was discussed rather than at every file an agent happened to read. Titles come from each tool's own session names where they exist (Claude Code's /rename and generated titles, Codex thread names), falling back to the first prompt.
You need session history from at least one of Claude Code, Codex CLI, Cursor, Antigravity, or Pi.
curl --proto '=https' --tlsv1.2 -LsSf https://github.com/braincompany/sessiongrep/releases/latest/download/sessiongrep-installer.sh | sh
The installer picks the build for your platform, verifies its checksum, and adds ~/.cargo/bin to your PATH if needed. Archives for manual download are on the releases page.
Requires a Rust toolchain 1.88 or newer:
cargo install sessiongrep --locked
To build the latest main instead: cargo install --locked --git https://github.com/braincompany/sessiongrep. Nix users can install from the flake: nix profile install github:braincompany/sessiongrep.
Every method installs two binaries into ~/.cargo/bin/:
sessiongrep — CLI and TUIsessiongrep-mcp — MCP serverTo upgrade, run the same command again.
The index updates automatically — every command (search, list, tui, etc.) runs an incremental reindex before executing. No cron jobs or manual steps needed.
To force a full rebuild from scratch (see Privacy & data for what this drops):
sessiongrep reindex --full
sessiongrep list --limit 20 # recent sessions (auto-indexes on first run)
sessiongrep search "auth bug" # keyword search
sessiongrep search "redis" --provider codex
sessiongrep search "datadog" --provider cursor
sessiongrep search "temporal" --provider pi
sessiongrep show claude:79accec8-5bf5-415b-a4a5-fe370eb2c998
sessiongrep resume 79accec8 --dry-run
sessiongrep export 79accec8 --format markdown
sessiongrep doctor # health check
sessiongrep tui # interactive browser
sessiongrep --help # every command and flag
Search matches whole words, partial words (sqli finds sqlite), and small typos in titles and paths, then ranks results by where the match landed, how recent the session is, and whether it belongs to the repo you're in.
The MCP server lets AI agents search and retrieve your past sessions programmatically — no copy-pasting context from old conversations.
claude mcp add --scope user --transport stdio sessiongrep -- sessiongrep-mcp
codex mcp add sessiongrep -- sessiongrep-mcp
Start a new session and try a prompt like:
"Find my previous session where I was setting up Datadog metrics"
The agent will call search_sessions to find matches and get_session to pull in relevant context.
Optional config file at ~/.config/sessiongrep/config.toml. Every key is optional; these are the defaults:
[providers.claude]
enabled = true
paths = ["~/.claude/projects"]
[providers.codex]
enabled = true
paths = ["~/.codex/sessions"] # or $CODEX_HOME/sessions when CODEX_HOME is set
[providers.cursor]
enabled = true
paths = ["~/.cursor/projects"]
[providers.antigravity]
enabled = true
paths = ["~/.gemini/antigravity/brain"]
[providers.pi]
enabled = true
paths = ["~/.pi/agent/sessions"]
[index]
db_path = "~/.local/share/sessiongrep/index.db"
[search]
default_limit = 25 # results for list/search when --limit isn't given
prefer_current_repo = true # rank sessions from the repo you're in higher
~/.local/share/sessiongrep/index.db is built from your transcripts and can be deleted anytime.cleanupPeriodDays setting). Deleting the index or running reindex --full rebuilds it from the files still on disk and drops those sessions.~/.local/share and ~/.config.claude --resume <id>, codex resume <id>, or pi --session <id>). Cursor and Antigravity resume are not currently supported, and a session whose transcript file has been deleted can be searched but not resumed.Early but usable (v0.1). The CLI surface and MCP tool names are likely to stay stable. When an upgrade changes how sessions are parsed, sessiongrep re-parses your session files automatically on the next run.
Issues and pull requests are welcome. For bugs, please include your provider versions and a sessiongrep doctor output. For features, a quick issue to discuss scope before sending a PR keeps things moving.
Apache-2.0. See LICENSE.
Local-first memory layer for CLI agents. Indexes Claude Code, Codex CLI, Cursor, Antigravity, and Pi sessions into SQLite + FTS5, searchable from a CLI, TUI, or MCP server.
Инструменты
Списка инструментов пока нет. У удалённых серверов он появляется после первой проверки состояния.
FAQ
Скопируйте на этой странице конфигурацию stdio для Cursor, Claude Desktop, Claude Code или VS Code. Она использует установку издателя, а не прокси PlugMCP.
В этой записи не указано обязательных переменных окружения.
Sessiongrep работает локально через stdio.
Последняя проверка: 2026-10-28. Local-first memory layer for CLI agents. Indexes Claude Code, Codex CLI, Cursor, Antigravity, and Pi sessions into SQLite + FTS5, searchable from a CLI, TUI, or MCP server.
