New: Auditable Call Memory

Auditable Call Memory for any AI phone agent

When a returning caller dials your AgentCall number, your AI gets a one-paragraph brief on who they are, what they last asked about, and what was promised. Every memory entry quotes the line from the transcript that produced it. Owners audit and correct anything wrong from the dashboard.

On
By default
Source
Backed by transcript quotes
Toggle
Off any time from dashboard
$0
Extra on Pro

Three things Auditable Call Memory does

Source-backed, auditable, and entirely under your control.

Cross-call memory

Sarah called Tuesday about a quote. Friday, she calls back, and your AI already knows it is Sarah, knows about the quote, and picks up the thread. No re-asking name, no starting over.

Auditable

Every memory entry quotes the verbatim line from the transcript that produced it, with the callId it came from. Review, edit, or delete any entry from the dashboard. Nothing in your AI's head you cannot trace back to a real conversation.

Customer-controlled

A Cross-call memory toggle on the dashboard overview turns it off at any time. On by default. Takes effect immediately. Never retroactively processes old calls when you flip it back on.

How Auditable Call Memory works

Four steps. All automatic. No multi-week integration.

Step 1

A call happens

Your virtual agent answers, or AgentCall hands the call to your own agent. The full conversation is transcribed in real time.

Step 2

Extracted to a Call Report

When the call ends, AgentCall produces a structured Call Report: who called, what they asked, what was promised, what to follow up on. Each entry is bound to a quote from the transcript.

Step 3

Memory persists

Approved memory entries are filed against the caller. Owners can edit or delete any entry from the dashboard before or after it is used.

Step 4

Next call gets a brief

The moment the same caller dials back, your AI receives a one-paragraph brief plus the underlying memories. The conversation picks up where it left off.

A working example: get_next_call_context

One call. Returns the brief your AI needs to speak with full context. Use it from MCP inside Claude or Cursor, the SDK, or plain REST.

GET /v1/memory/next-call-context
curl https://api.agentcall.co/v1/memory/next-call-context \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -G --data-urlencode "phone=+14155550142"
200 OK
{
  "caller": {
    "name": "Sarah Chen",
    "phone": "+14155550142",
    "firstSeenAt": "2026-05-12T14:03:21Z",
    "callCount": 3
  },
  "brief": "Sarah called Tuesday asking about pricing for a 30-person team. You promised to send a quote by Friday. She mentioned a competitor demo on Thursday.",
  "memories": [
    {
      "id": "mem_8h2k",
      "fact": "Team size is approximately 30 people",
      "source": "Yeah we're a team of about 30",
      "fromCallId": "call_x7k9m2",
      "recordedAt": "2026-05-12T14:05:11Z"
    },
    {
      "id": "mem_9p4n",
      "fact": "Promised a written quote by Friday",
      "source": "Can you send a quote by Friday?",
      "fromCallId": "call_x7k9m2",
      "recordedAt": "2026-05-12T14:06:48Z"
    }
  ]
}

The same data is available via the get_next_call_context MCP tool. Full payload and event types at /docs/memory.

Integration patterns

Auditable Call Memory works with any AI phone agent. Pick the pattern that matches how your agent is built.

MCP from Claude, Cursor, Windsurf, OpenClaw

Drop the AgentCall MCP server into your client. 60 tools and 5 prompts auto-discover, including get_next_call_context, list_contacts, get_memory_timeline, and approve_memory_candidate. Your agent reads memory and acts on it from the same surface.

{
  "mcpServers": {
    "agentcall": {
      "transport": "streamable-http",
      "url": "https://api.agentcall.co/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Webhook to your own brain

Use the pre-call context webhook to inject memory at the start of every inbound call, and the post-call transcript webhook to feed fresh Call Reports back into your platform. HMAC-signed, retried with backoff. Open-source Cloudflare Worker template available.

AgentCall virtual agent (zero config)

Configure inbound AI on any AgentCall number, write your system prompt, and memory is wired in automatically. Returning callers get recognized and the brief is loaded before the AI speaks. No code required.

Hermes, OpenClaw, or any agent platform

Wire the pre-call context webhook to your agent platform so the brief gets composed by your own brain. Memory is still extracted and stored by AgentCall; your platform decides which pieces to surface on the next call. Hermes setup guide.

What you can build with Auditable Call Memory

Every example below is shipping today on AgentCall.

Virtual agent that remembers callers

Your customer calls Tuesday about a quote. They call again Friday. Your AI greets them by context: 'Hi Sarah, are you calling back about the quote we discussed Tuesday?' No re-introduction, no re-asking what it is about.

Sales agent that learns from every call

Each Call Report feeds your CRM. Your AI reads prior conversation history before dialing the next prospect, references what was already discussed, and never restarts qualification from scratch.

Support agent that picks up the thread

Customer calls Monday and gets routed to your AI for triage. Calls back Tuesday. Your agent already knows the issue, the steps tried, and what to try next.

Outbound campaign that does not repeat itself

Your AI agent makes follow-up calls based on outcomes from the prior round. Anyone who said 'call me Tuesday' gets a Tuesday call referencing the previous conversation.

Pricing

No separate memory charge. Memory is included on Pro, and Free is capped naturally by the inbound AI trial.

Free
$0
  • 5 minutes of inbound AI voice per month
  • Memory builds up to the trial cap (no extra charge)
  • Dashboard audit and toggle
Pro
$19.99 / month
  • Auditable Call Memory included, no separate fee
  • Inbound AI voice at $0.40 / minute, no monthly cap
  • Full MCP surface: 60 tools and 5 prompts

Give your AI phone agent a memory it can prove.

Free tier includes one US local number, 5 minutes of inbound AI voice per month, and the dashboard audit view. No card required to start.

Or read the docs: Auditable Call Memory · Post-call Transcript Webhook · MCP Server · FAQ

Frequently asked questions

What is Auditable Call Memory?+

Auditable Call Memory is a source-backed memory layer extracted from completed AI calls. When a returning caller dials your AgentCall number, your AI receives a one-paragraph brief with who they are, what they last asked about, and what was promised. Every memory entry quotes the transcript line that produced it so owners can audit and correct anything wrong from the dashboard.

Does this work with any AI phone agent or only Hermes?+

It works with any AI phone agent. AgentCall's own virtual agent uses it out of the box. You can also pull memory into Claude, Cursor, Windsurf, OpenClaw, or your own agent platform via the MCP server, the pre-call context webhook, or the REST API. Hermes is one supported brain among many.

How do I turn cross-call memory off?+

There is a Cross-call memory toggle on the dashboard overview. Turning it off takes effect immediately. It is on by default for new accounts and never retroactively processes past calls.

What does a memory entry look like?+

Each entry has a subject (the caller or topic), a short fact, a source quote pulled directly from the transcript, the callId it came from, and a timestamp. Owners can edit or delete any entry from the dashboard.

What does Auditable Call Memory cost?+

There is no separate charge for memory on the Pro plan ($19.99/month). The Free plan is naturally capped by the 5-minute monthly inbound AI voice trial, so memory only builds up to the limit of what your free trial covers.