
๐ง Turn your AI coding sessions into a searchable, interlinked wiki. Claude Code, Codex CLI, Cursor
๐ง Turn your AI coding sessions into a searchable, interlinked wiki. Claude Code, Codex CLI, Cursor, Gemini CLI, ZCode, OpenCode & Obsidian โ a Karpathy-style LLM Wiki with LLM synthesis, a session graph, a static site and an MCP server. Local-first. Based on llmwiki by Pratiyush.
ยท
Your AI coding sessions, compiled into a searchable, interlinked wiki โ from Claude Code, Codex CLI, Cursor, Gemini CLI, Copilot, ZCode and OpenCode. Local-first, with LLM synthesis, a session graph, and an MCP server so your agents can look up what you already solved.
27 synthetic sessions across five projects and seven agents (AugโNov 2026) โ no personal data. Rebuilt from examples/demo-sessions/ on every push to master.
Every agent you work with writes a full transcript to disk: the plan, the dead ends, the fix, the reasoning behind it. Hundreds of them, in five different formats, and you never look at them again.
sessionwiki turns that history into a knowledge base:
sessionwiki audit checks the output before you publish anything.Already using Claude Code's built-in memory, claude-mem or a session search tool? The FAQ explains what sessionwiki adds โ and when another tool is the better choice.
| 10 sources | Built in: Claude Code, Codex CLI, ZCode, OpenCode. Opt-in: Cursor, Gemini CLI, Copilot Chat, Copilot CLI, ChatGPT export, Obsidian โ each with its own agent badge |
| Autosync | Claude Code Stop hook, ZCode Stop hook + nightly systemd / launchd / Task Scheduler job, OpenCode session.idle plugin |
| Synthesis backends | extractive (default, no model), Ollama, any OpenAI-compatible server (vLLM, SGLang, LM Studio, LiteLLM, hosted), agent-delegate, offline dummy |
| Signal over noise | Low-signal session coalescing, wikilink cleanup, concurrency control, cost --estimate |
| Static site | 365-day heatmap, token and cache stats, filterable sessions table, session pages with highlighted code, project pages with topics, session โ project graph, โK search, dark mode |
| MCP server | 15 tools: query, search, read, list sources, lint, sync, exports, dashboard, write/edit/archive pages (with a confirm step)โฆ |
| AI exports | llms.txt, llms-full.txt, JSON-LD graph, per-page .txt / .json, sitemap, RSS |
| Safe by default | Redaction of usernames and 17 secret patterns, read-only database exports, OS file locks and atomic state writes, doctor and audit |
All screenshots come from the live demo and are regenerated with scripts/regen_docs_screenshots.py.
Every session, every agent โ filter by project, model and date; each row carries its agent badge.
Session pages โ the summary, the conversation, highlighted code and the tools that ran, plus token and cache usage.
Projects โ topics, description, activity and tool usage per project, with freshness badges on the index.
![]() | ![]() |
|---|
Graph and search โ sessions grouped around their projects; โK searches every page instantly.
![]() | ![]() |
|---|
git clone https://github.com/necroz/sessionwiki.git
cd sessionwiki
./setup.sh # Windows: setup.bat โ creates .venv, detects your agents
./sync.sh # convert new sessions into raw/
./build.sh && ./serve.sh # build the site and open http://127.0.0.1:8765setup creates a checkout-local .venv, installs the package, scaffolds raw/, wiki/, site/, enables the adapters for the agents it finds and runs sessionwiki doctor. The wrapper scripts use the venv automatically; for the CLI, activate it (source .venv/bin/activate) or call .venv/bin/sessionwiki.
Or install the published package โ pick one:
uv tool install sessionwiki # uv: CLI in its own isolated environment
uvx sessionwiki --help # uv: run without installing
pip install sessionwiki # pip, inside a virtualenv
pip install 'sessionwiki[graph]' # + graphify graph engine (also works with uv tool install)Docker โ serve a site you have built (image ghcr.io/necroz/sessionwiki, see Docker deployment for docker compose and running CLI commands in the container):
docker run --rm -p 8765:8765 -v "$PWD/site:/wiki/site:ro" ghcr.io/necroz/sessionwikiA step-by-step walkthrough with screenshots lives in the setup guide.
Claude Code, Codex CLI, Cursor, Gemini CLI, Copilot โ read straight from their session folders on sessionwiki sync. To sync after every Claude Code reply, add a Stop hook to ~/.claude/settings.json:
{
"hooks": {
"Stop": [{ "hooks": [{ "type": "command",
"command": "cd /path/to/sessionwiki && .venv/bin/python -m sessionwiki sync --no-auto-build >/dev/null 2>&1 &" }] }]
}
}Parallel hook runs are safe: sync and synthesize take an OS file lock and write their state atomically.
To add related past work to every prompt, opt in to a UserPromptSubmit hook โ it is off unless SESSIONWIKI_PROMPT_RECALL=1 is set. It injects up to three related pages plus up to three approved lessons (wiki/lessons/, lifecycle reviewed or verified); draft lessons never reach the prompt:
{
"hooks": {
"UserPromptSubmit": [{ "hooks": [{ "type": "command", "timeout": 10,
"command": "cd /path/to/sessionwiki && SESSIONWIKI_PROMPT_RECALL=1 .venv/bin/python -m sessionwiki recall --prompt-hook" }] }]
}
}Cost: two wiki scans per prompt (pages, then lessons). A single scan measured a median of 170 ms with three pages returned, 140 ms when nothing matches (before lessons landed).
ZCode keeps sessions in SQLite. sessionwiki exports them read-only and installs the hook and a nightly job for you:
sessionwiki zcode install --dry-run # show what will be written
sessionwiki zcode install # Stop + SessionStart hooks, systemd / launchd / Task SchedulerOpenCode (V2, opencode.db) gets a server plugin that runs autosync when a session goes idle:
sessionwiki opencode install --dry-run
sessionwiki opencode install # honours $XDG_CONFIG_HOMEHook-triggered runs skip instead of queueing when a cycle is already running; scheduled runs wait and catch up. Details: ZCODE.md, docs/adapters/opencode.md, and sessionwiki adapters for the full list.
sync fills raw/ with redacted transcripts. synthesize turns them into wiki pages: a summary per session, project pages, cross-links. Point it at any backend in config.local.json:
{
"synthesis": {
"backend": "openai",
"base_url": "http://127.0.0.1:8000/v1",
"model": "qwen3-coder",
"max_concurrency": 8,
"coalesce_low_signal": true
}
}sessionwiki synthesize --estimate # what it will cost before you run it
sessionwiki synthesize # new sessions only; idempotent
sessionwiki all --with-synth # synthesize โ build โ graph โ export โ lintBackends: extractive (the default โ no model and no network: a useful page from the transcript itself), ollama (local), openai (any OpenAI-compatible /v1: vLLM, SGLang, LM Studio, LiteLLM, hosted APIs), agent-delegate (let your coding agent write the pages), dummy (offline metadata stubs). sessionwiki warns when a non-loopback base_url would send transcripts off your machine. See docs/modes/api/.
Claude Code plugin โ the MCP server, a skill that tells the agent when to search the wiki, and a SessionStart hook that puts the project's recent sessions into context. It asks for your sessionwiki folder on install:
/plugin marketplace add necroz/sessionwiki
/plugin install sessionwiki@sessionwikiAny MCP client โ run the published package with uvx, and point SESSIONWIKI_HOME at the folder that holds raw/ and wiki/ (run sessionwiki sync there first):
{
"mcpServers": {
"sessionwiki": {
"command": "uvx",
"args": ["sessionwiki", "mcp"],
"env": { "SESSIONWIKI_HOME": "/path/to/your/sessionwiki" }
}
}
}From a source checkout, use "command": "/path/to/sessionwiki/.venv/bin/sessionwiki" with "args": ["mcp"]; the checkout is the data root, so no env is needed.
Add it to Claude Code, Claude Desktop, ZCode or any MCP client. Tools include wiki_query (ranked search over wiki pages in any language, falling back to raw transcripts), wiki_search (exact text, optionally over raw transcripts), wiki_read_page, wiki_list_sources, wiki_lint, wiki_sync, wiki_export, wiki_dashboard and more โ 15 in total, stdio transport, no SDK dependency, path-traversal guarded.
sessionwiki init # scaffold raw/ wiki/ site/
sessionwiki sync # export ZCode/OpenCode + convert transcripts to markdown
sessionwiki synthesize # LLM summaries into wiki/ (--estimate, --coalesce-only, --force)
sessionwiki build # static site + AI exports
sessionwiki serve # local server on 127.0.0.1:8765
sessionwiki all # build โ graph โ export โ lint (add --with-synth)
sessionwiki query "<question>" # ask the wiki a question from the terminal
sessionwiki graph # session/project and wikilink graph
sessionwiki lint # wiki lint rules
sessionwiki export # llms.txt, JSON-LD, sitemap, RSS, โฆ
sessionwiki candidates # review candidate pages
sessionwiki adapters # available adapters and their state
sessionwiki doctor # check Python, deps, config, agent paths
sessionwiki audit # scan raw/ wiki/ site/ for usernames and secrets
sessionwiki zcode # export ยท autosync ยท install
sessionwiki opencode # export ยท autosync ยท install
sessionwiki mcp # MCP server on stdio
sessionwiki recall # a project's recent sessions, for a SessionStart hook
sessionwiki versionEvery subcommand has --help. Full reference: docs/reference/cli.md.
Settings are layered; later files win:
examples/sessions_config.json โ config.json โ config.local.json
(shared defaults) (gitignored) (gitignored, machine-local)Put machine-specific values โ synthesis backend and keys, redaction patterns, project roots, adapter toggles โ in config.local.json. Reference: docs/configuration-reference.md. Use .llmwikiignore to exclude projects or sessions.
Claude Code ยท Codex ยท Cursor ยท Gemini ยท Copilot ZCode ยท OpenCode (SQLite)
โ JSONL โ read-only export
โโโโโโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโ
โผ
sync โ raw/sessions/*.md redacted, immutable
โ
synthesize โผ
wiki/ sources ยท projects ยท entities ยท concepts
โ
โโโโโโโโโโโโโโโโโโผโโโโโโโโโโโโโโโโโโโ
โผ โผ โผ
build โ site/ MCP server exports (llms.txt, JSON-LD)Three layers, following Karpathy's LLM Wiki pattern: raw/ is the immutable source of truth, wiki/ is maintained by the LLM, site/ is generated. Your raw/ and wiki/ are gitignored โ your data never enters the repository.
sessionwiki audit scans raw/, wiki/ and site/ before you publish a site.See docs/privacy.md and SECURITY.md.
sessionwiki started as a fork of llmwiki by Pratiyush (MIT) at v1.3.82 and keeps its full history. Most of the converter, site, lint and MCP foundations are his work. sessionwiki adds the ZCode and OpenCode sources with autosync, the OpenAI-compatible synthesis backend, session coalescing, locking and atomic state, doctor and audit, the session graph, and a long list of fixes โ see what's different and how to migrate.
Thanks also to Andrej Karpathy for the LLM Wiki idea, Python Markdown, highlight.js and vis-network.
Read CONTRIBUTING.md. Keep PRs to one concern, use feat: / fix: / docs: / chore: / test: titles, add a CHANGELOG entry for feat and fix, and never commit real session data. CI must be green.
MIT ยฉ 2026 Igor Lashkevich (sessionwiki) ยท ยฉ 2026 Pratiyush (original llmwiki). See NOTICE.
Pick your client and paste the snippet. Each one is the same server, written the way that client expects it.
claude mcp add sessionwiki -- uvx sessionwiki mcp{
"mcpServers": {
"sessionwiki": {
"env": {
"SESSIONWIKI_HOME": ""
},
"args": [
"sessionwiki",
"mcp"
],
"command": "uvx"
}
}
}code --add-mcp '{"name":"sessionwiki","env":{"SESSIONWIKI_HOME":""},"args":["sessionwiki","mcp"],"command":"uvx"}'[mcp_servers.sessionwiki]
command = "uvx"
args = ["sessionwiki", "mcp"]Runs locally on your device. Your client starts the server itself, so nothing has to be hosted.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/sessionwiki to learn what the "sessionwiki" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
uvx sessionwiki --help # uv: run without installingdocker run --rm -p 8765:8765 -v "$PWD/site:/wiki/site:ro" ghcr.io/necroz/sessionwikiuv tool install sessionwikipip install sessionwiki
pip install 'sessionwiki[graph]'This server runs locally, so we can't read its tool list over the web yet.
We could not run this server: it ships no npx package for our sandbox and no public endpoint. The four checks that need a live server are left out, and the grade tops out at B until one exists.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/sessionwiki)Nothing comparable is listed yet.
v2.3.0Release notesv2.2.0Release notesv2.1.0Release notesv2.0.5Release notesv2.0.4Release notesv2.0.3Release notesv2.0.2Release notesv2.0.1Release notesv2.0.0Release notesConnect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "sessionwiki" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.