Recall gives Claude Code a permanent memory store that survives every session restart and context compaction β automatically. Install the plugin once and four hooks capture context and restore it on every session, with zero prompting required.
Live activity as you work:Recall: 1.0.0 π§ 7 (4s ago)Version Β· memory count Β· time since last store
{
"mcpServers": {
"recall": {
"url": "https://recallmcp.com/mcp",
"headers": {
"Authorization": "Bearer YOUR_KEY"
}
}
}
}Clear expectations for what Recall does and doesn't do.
Cross-session memory β Knowledge persists between conversations. Start a new chat and retrieve previous decisions.
Survives context compaction β When Claude's context window fills up and gets summarized, your memories remain intact externally.
Real-time team collaboration β One Claude learns something, all others know instantly. Share across 10s-1000s of instances.
Long-term knowledge base β Store decisions, patterns, and preferences that accumulate over weeks and months.
Fully automatic with hooks β Install Claude Code hooks once and memory capture happens automatically on every session.
Not within-conversation compression β Your current chat still grows with each message. Recall helps across sessions, not within one.
Semi-automatic β Claude calls tools proactively, but you guide what's important. Not magic context reduction.
Not a replacement for good prompting β Store high-signal information (decisions, patterns), not everything.
Not instant token savings β Benefits compound over time as knowledge accumulates externally.
Built for developers who want their AI agents to remember conversations, learn patterns, and maintain context across sessions.
Install once with one command β four hooks capture context and restore it automatically on every Claude Code session.
Named workflow threads that span multiple sessions with automatic memory tagging and context threading.
Automatically cluster and merge similar memories. Keep originals as history, surface consolidated summaries.
Track tasks across sessions with priority levels and defer tracking. Pending to-dos auto-inject into every session start.
Vector embeddings with cosine similarity. Find memories by meaning, not just keywords.
Complete data isolation per API key. Your memories are yours alone.
AES-256-GCM encryption at rest. Per-tenant keys derived via HKDF. SOC 2 ready.
Voyage AI, Cohere, OpenAI, Deepseek, Grok, Anthropic, or self-hosted Ollama.
First-class Model Context Protocol support. Works with Claude, Cursor, and more.
Simple HTTP endpoints for any client. CRUD operations, search, and batch processing.
Organize memories by type: decisions, patterns, preferences, errors, and more.
One Claude learns, all others know instantly. Share knowledge across 10s-1000s of instances in real-time.
When context windows fill up and get summarized, your memories persist externally for retrieval.
Receive events from GitHub, Stripe, or any service and route them directly into your Claude sessions β with HMAC signature verification.
Full audit trail of every webhook event β queued, filtered, or blocked. Replay any past event into your queue with one click.
Real-world scenarios where persistent memory makes Claude dramatically more useful β across sessions, projects, and teams.
Pick up a complex feature after the weekend. Recall loads past decisions, patterns, and context automatically β Claude continues from where you left off.
/loop 3m check if the deployment finished. Claude monitors your Railway or Vercel deploy in the background while you keep coding.
Chasing a race condition across three days? Recall stores every hypothesis, what you tested, and what you ruled out β so each session builds on the last.
Every architectural choice is captured with its reasoning at the moment it's made. No Confluence page needed β the context lives with the code.
Work across 5 codebases. Each git remote maps to an isolated memory namespace. Claude always knows which project's conventions apply.
When Claude's context window fills up, Recall's hooks snapshot state before compaction and restore it after β sessions continue seamlessly.
One developer discovers a critical pattern. Claude stores it globally. Every team member's Claude loads it at session start, automatically.
Persistent to-dos that survive session restarts. Combine with /loop for hourly reminders β full task continuity without a separate ticket system.
Recall listens for webhooks from any service β Sentry, GitHub, Honeybadger, Slack, Linear, PagerDuty, Stripe, Discord, or your own system β and routes them directly into your Claude sessions. No polling. No glue code. Just events.
External Service
Sentry Β· GitHub Β· Slack Β· Any webhook
Recall
Verify Β· Filter Β· Route
Event Queue
History Β· Replay Β· Audit
Claude Session
Workspace-routed
Push event triggers webhook delivery:
https://recallmcp.com/api/webhooks/events \
-H "X-Recall-Signature: sha256=a3f9β¦" \
-d '{"event":"push","repo":"my-app","commits":3}'
β HTTP 200 OK
{"success":true,"data":{"queued":true}}
[Recall] Restoring session contextβ¦
[Recall] π 1 pending webhook event
Listening for eventsβ¦
github β push
repo: my-app
commits: 3 to main
workspace: my-app β
First-seen sources need your approval
Cryptographic proof every event is genuine
Set a signing secret per source. Recall verifies every incoming request with timing-safe HMAC-SHA256 before it touches your queue.
Wrong or missing signature β 401. No secret configured β works as before, no breaking change.
Full audit trail with one-click replay
Sending a signed webhook to Recall
BODY='{"event":"push","repo":"my-app","commits":3}'
SECRET="whsec_your_signing_secret"
SIG=$(echo -n "$BODY" | openssl dgst -sha256 -hmac "$SECRET" -hex | awk '{print "sha256="$2}')
curl -X POST https://recallmcp.com/api/webhooks/events?token=sk-xxx \
-H "Content-Type: application/json" \
-H "X-Recall-Signature: $SIG" \
-d "$BODY"Errors and issues injected into Claude automatically via Internal Integration.
Push events, PRs, and issues routed to the right workspace automatically.
Errors and uptime alerts arrive in Claude before you even open the dashboard.
Messages and commands forwarded to Claude for processing.
Issue updates and assignments surfaced in your coding session.
On-call incidents delivered to Claude with full context.
Payment events, subscription changes, and failed charges captured in context.
Any system that can send an HTTP POST. No SDK required.
Attach custom instructions to any webhook source
Event Prompts let you configure codebase-specific guidance that Claude receives alongside every event. Tell Claude which files to check first, what your incident protocol is, known failure modes, and service-specific quirks β so it doesn't start from scratch every time.
Auto-Memory Hooks wire Recall directly into Claude Code. One command installs four hooks β context loads at session start, key actions are captured silently, and hooks keep themselves up to date.
β "Let me re-explain the project again..."
β "Remember, we use JWT for auth, not sessions"
β "Where did we leave off last time?"
β Context lost every session restart
β Context loaded automatically at session start
β Decisions captured after every significant change
β Session summaries picked up next time
β Works silently β zero extra prompts
Included with the Recall plugin β or install hooks standalone:
Fires when Claude Code starts
Fires after Write / Edit / Task
Fires before context compaction
Fires when Claude Code exits
Start free, scale as you grow. No hidden fees, no usage surprises.
Most Popular | ||||
|---|---|---|---|---|
| Memory | ||||
| Memories | 500 | 5,000 | 25,000 | Unlimited |
| Workspaces | 1 | 3 (+ add-ons)β | 25 (+ add-ons)β | Unlimited |
| Semantic search | ||||
| Cross-session workflows | ||||
| Auto-consolidation | ||||
| Survives compaction | ||||
| Webhooks | ||||
| Webhook events / month | β | 1,000 (+ packs)β | 5,000 (+ packs)β | Unlimited |
| Webhook filters | β | 25 | 100 | Unlimited |
| HMAC signature verification | ||||
| Event history & replay | ||||
| Workspace routing | ||||
| Team & Security | ||||
| Team members | 1 | 1 | 10 | Unlimited |
| Shared memories | ||||
| Audit logging | ||||
| REST API | ||||
| Support | Community | Priority | Priority | Community |
β Add-ons available on Pro & Team: $0.99/workspace/month Β· $1.99 per 1,000 webhook events/month
Full data sovereignty, unlimited memories, and a polished one-command installer. Deploy on any server that can run Docker.
Detects Docker, configures Redis + Recall, prints your MCP config.
No plan caps. Store as many memories as your server can handle.
Your memories never leave your infrastructure. Zero cloud dependency.
Redis + Recall server up in under 2 minutes with a single curl command.
Activate with a license key. Works air-gapped with a 7-day grace window.
From signup to AI with memory in just a few steps.
Create your free account. No credit card required.
Generate your API key from the dashboard.
Two commands in Claude Code to install the Recall plugin.
Your AI now has persistent memory across sessions.