# Past.dev

```json
{
  "name": "Past.dev",
  "slug": "past_dev",
  "url": "https://composio.dev/toolkits/past_dev",
  "markdown_url": "https://composio.dev/toolkits/past_dev.md",
  "logo_url": "https://logos.composio.dev/api/past_dev",
  "categories": [
    "ai & machine learning"
  ],
  "is_composio_managed": false,
  "updated_at": "2026-11-06T05:31:17.889Z"
}
```

![Past.dev logo](https://logos.composio.dev/api/past_dev)

## Description

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Past.dev MCP or direct API to ingest memories, recall source-backed context, inspect memory traces, and clean up stored data through natural language.

## Summary

Past.dev is a source-backed memory service for AI agents.
It helps agents retain, trace, and safely manage durable context.

## Categories

- ai & machine learning

## Toolkit Details

- Tools: 29

## Images

- Logo: https://logos.composio.dev/api/past_dev

## Authentication

- **Api Key**
  - Type: `api_key`
  - Description: Api Key authentication for Past.dev.
  - Setup:
    - Configure Api Key credentials for Past.dev.
    - Use the credentials when creating an auth config in Composio.

## Suggested Prompts

- Recall product decisions from last quarter
- Inspect memory traces for recent requests
- Clean up memories tied to old projects

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `PAST_DEV_BULK_REPLACE_IDENTITIES` | Replace Identities in Bulk | Atomically create or replace complete trait sets for up to 1,000 identities; omitted traits replace the identity with no traits. |
| `PAST_DEV_DELETE_AUDIENCE` | Delete Audience | DESTRUCTIVE ACCESS CHANGE: Permanently delete an audience. Its stored memory remains but becomes permanently unreachable. The default project audience cannot be deleted. |
| `PAST_DEV_DELETE_IDENTITY` | Delete Identity | DESTRUCTIVE: Permanently delete an identity directory record and remove it from every audience. Stored memory associated with the identity remains and is not deleted. |
| `PAST_DEV_DELETE_INGESTION_MEMORY` | Permanently Delete Ingestion Memory | DESTRUCTIVE: Permanently delete every data point accepted by one ingestion and memory depending only on those points. This cannot be undone; the ingestion status and audit record remains readable. |
| `PAST_DEV_DELETE_MEMORY_DATA_POINT` | Delete Memory Data Point | DESTRUCTIVE: Permanently delete one data point by its caller-owned source id and remove memory derived from it. This cannot be undone; the purge completes asynchronously. |
| `PAST_DEV_DELETE_MEMORY_DATA_POINTS` | Delete Memory Data Points | DESTRUCTIVE: Permanently and atomically delete up to 1,000 data points by caller-owned source id and remove memory derived from them. This cannot be undone; the purge completes asynchronously. |
| `PAST_DEV_ESTIMATE_INGESTION` | Estimate Ingestion | Cut files into data points, plan batches, and estimate credits without storing data or spending credits. |
| `PAST_DEV_EXPLAIN_INGESTION` | Explain Ingestion | Diagnose how far one send progressed, including per-item searchability, memory counts, failure details, and the recommended next step. |
| `PAST_DEV_FIND_TRACE_ROOTS` | Find Trace Roots | Find memory and source nodes for lineage or timeline inspection, returning independent memory and source cursors. |
| `PAST_DEV_GET_AUDIENCE` | Get Audience | Read one fixed, rule, or default audience with its definition and current membership and memory counts. |
| `PAST_DEV_GET_IDENTITY` | Get Identity | Return one identity's traits, origin, timestamps, and current audience memberships. |
| `PAST_DEV_GET_INGESTION_STATUS` | Get Ingestion Status | Poll one ingestion for processing, completion, failure, and project readiness without consuming metered request quota. |
| `PAST_DEV_GET_REQUEST` | Get API Request | Read one API call and its retained allowlisted headers and request/response payload; bearer credentials are never returned. |
| `PAST_DEV_GET_REQUEST_HISTOGRAM` | Get Request Histogram | Count accepted, failed-later, and rejected API calls in provider-selected time buckets using request-log filters. |
| `PAST_DEV_GET_TRACE_LINEAGE` | Get Trace Lineage | Read what a memory or source was built from and what was built on it, including graph edges and hidden-node count. |
| `PAST_DEV_GET_TRACE_NODE` | Get Trace Node | Read one memory or source node with revision, validity, replacement, request, content, and graph counts. |
| `PAST_DEV_GET_TRACE_TIMELINE` | Get Trace Timeline | Read rooted source and memory work, ingestions, recalls, and supersessions on a clock for a window of at most 31 days. |
| `PAST_DEV_GET_USAGE` | Get Usage | Return the current UTC month's credit balance, metering state, and project ingestion, recall, and cap usage. |
| `PAST_DEV_INGEST_MEMORY` | Ingest Memory | Ingest one timestamped data point into durable memory, optionally associating it with an identity and audience; reusing an id replaces the prior revision when stored fields change. |
| `PAST_DEV_INGEST_MEMORY_BATCH` | Ingest Memory Batch | Atomically ingest 1 to 1,000 ordered memory data points in one request, avoiding fragile per-item agent loops. |
| `PAST_DEV_LIST_AUDIENCES` | List Audiences | List every audience in the connected project, including the default project audience and current membership and memory counts. |
| `PAST_DEV_LIST_IDENTITIES` | List Identities | List project identities newest first, optionally filtering by one trait, and return a cursor for the next page. |
| `PAST_DEV_LIST_REQUESTS` | List API Requests | List the connected project's API calls newest first, with filters and a cursor for the next page. |
| `PAST_DEV_RECALL_MEMORY` | Recall Memory | Return ranked, source-backed memory visible to an identity for a query, with optional time range, sort order, and evidence budget controls. |
| `PAST_DEV_RECOMPUTE_AUDIENCE` | Recompute Audience | Recompute an audience's membership from its definition and apply the refreshed access set to recall immediately. |
| `PAST_DEV_REPLACE_AUDIENCE` | Create or Replace Audience | Create or completely replace a fixed-list or trait-rule audience and its access definition. The default project audience cannot be replaced. |
| `PAST_DEV_REPLACE_IDENTITY` | Replace Identity | Create an identity or replace its complete trait set; omitted or empty traits remove all existing traits. |
| `PAST_DEV_RETRY_INGESTION` | Retry Ingestion | Retry a stopped or failed ingestion under its existing id without spending additional credits; completed ingestions are rejected. |
| `PAST_DEV_UPDATE_IDENTITY_TRAITS` | Update Identity Traits | Merge selected identity traits while preserving unspecified keys; set a trait value to null to remove that key. |

## Supported Triggers

None listed.

## Installation and MCP Setup

### Path 1: SDK Installation

#### Path 1, Step 1: Install Composio

Install the Composio SDK, the OpenAI provider, and the OpenAI SDK
```python
pip install composio composio_openai openai
```

```typescript
npm install @composio/core @composio/openai openai
```

#### Path 1, Step 2: Create a Composio session

Initialize Composio with the OpenAI Responses provider and create a session scoped to Past.dev
```python
import json
from openai import OpenAI
from composio import Composio
from composio_openai import OpenAIResponsesProvider

composio = Composio(provider=OpenAIResponsesProvider())
client = OpenAI()

session = composio.create(user_id="your-user-id", toolkits=["past_dev"])
tools = session.tools()
```

```typescript
import OpenAI from "openai";
import { Composio } from "@composio/core";
import { OpenAIResponsesProvider } from "@composio/openai";

const composio = new Composio({ provider: new OpenAIResponsesProvider() });
const client = new OpenAI();

const session = await composio.create("your-user-id", { toolkits: ["past_dev"] });
const tools = await session.tools();
```

#### Path 1, Step 3: Run Past.dev tools with your agent

Send a request, execute the Past.dev tool calls through the session, and print the final answer
```python
response = client.responses.create(
    model="gpt-5.6-sol",
    tools=tools,
    input=[{"role": "user", "content": "Recall source-backed memories about my product launch plans from last month"}],
)

while True:
    tool_calls = [o for o in response.output if o.type == "function_call"]
    if not tool_calls:
        break
    results = composio.provider.handle_tool_calls(response=response, session=session)
    response = client.responses.create(
        model="gpt-5.6-sol",
        tools=tools,
        previous_response_id=response.id,
        input=[
            {"type": "function_call_output", "call_id": call.call_id, "output": json.dumps(results[i])}
            for i, call in enumerate(tool_calls)
        ],
    )

print(response.output_text)
```

```typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "Recall source-backed memories about my product launch plans from last month" }],
});

while (response.output.some((o) => o.type === "function_call")) {
  const outputs = await composio.provider.handleToolCalls(session, response.output);
  response = await client.responses.create({
    model: "gpt-5.6-sol",
    tools,
    previous_response_id: response.id,
    input: outputs,
  });
}

console.log(response.output_text);
```

### Path 2: MCP Server Setup

#### Path 2, Step 1: Install Composio

Install the Composio SDK and your agent framework
```python
pip install composio claude-agent-sdk
```

```typescript
npm install @composio/core ai @ai-sdk/mcp @ai-sdk/openai
```

#### Path 2, Step 2: Create a session with MCP enabled

Create a session scoped to Past.dev and read its MCP URL and headers
```python
from composio import Composio

composio = Composio()
session = composio.create(user_id="your-user-id", toolkits=["past_dev"], mcp=True)
```

```typescript
import { Composio } from "@composio/core";

const composio = new Composio();
const { mcp } = await composio.create("your-user-id", {
  toolkits: ["past_dev"],
  mcp: true,
});
```

#### Path 2, Step 3: Connect your agent to the MCP server

Pass the session's MCP URL and headers to your agent and run a Past.dev request
```python
import asyncio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions, AssistantMessage, TextBlock

options = ClaudeAgentOptions(
    mcp_servers={
        "composio": {
            "type": "http",
            "url": session.mcp.url,
            "headers": session.mcp.headers,
        }
    },
    system_prompt="You are a helpful assistant with access to Past.dev tools.",
    tools=[],
    allowed_tools=["mcp__composio__*"],
)

async def main():
    async with ClaudeSDKClient(options=options) as client:
        await client.query("Recall source-backed memories about my product launch plans from last month")
        async for message in client.receive_response():
            if isinstance(message, AssistantMessage):
                for block in message.content:
                    if isinstance(block, TextBlock):
                        print(block.text)

asyncio.run(main())
```

```typescript
import { createMCPClient } from "@ai-sdk/mcp";
import { openai } from "@ai-sdk/openai";
import { generateText, stepCountIs } from "ai";

const client = await createMCPClient({
  transport: { type: "http", url: mcp.url, headers: mcp.headers },
});

const { text } = await generateText({
  model: openai("gpt-5.6-sol"),
  tools: await client.tools(),
  prompt: "Recall source-backed memories about my product launch plans from last month",
  stopWhen: stepCountIs(10),
});

console.log(text);
await client.close();
```

## Why Use Composio?

### 1. AI Native Past.dev Integration

- Supports both Past.dev MCP and direct API based integrations
- Structured, LLM-friendly schemas for reliable memory ingestion, recall, and diagnostics
- Rich coverage for identities, audiences, usage, request logs, traces, and cleanup

### 2. Managed Auth

- Securely stores and supplies your Past.dev API key during tool execution
- Central place to manage, scope, and revoke Past.dev access
- Per user and per environment credentials instead of hard-coded keys

### 3. Agent Optimized Design

- Tools are tuned using real error and success rates to improve reliability over time
- Comprehensive execution logs so you always know what ran, when, and on whose behalf

### 4. Enterprise Grade Security

- Fine-grained RBAC so you control which agents and users can access Past.dev
- Scoped, least privilege access to Past.dev resources
- Full audit trail of agent actions to support review and compliance

## Use Past.dev with any AI Agent Framework

Choose a framework you want to connect Past.dev with:

- [ChatGPT](https://composio.dev/toolkits/past_dev/framework/chatgpt)
- [Claude Cowork](https://composio.dev/toolkits/past_dev/framework/claude-cowork)
- [Hermes](https://composio.dev/toolkits/past_dev/framework/hermes-agent)
- [Atomic Agent](https://composio.dev/toolkits/past_dev/framework/atomic-agent)

## Related Toolkits

- [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed.
- [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service.
- [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows.
- [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow.
- [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows.
- [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application.
- [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities.
- [AltTextLab](https://composio.dev/toolkits/alt_text_lab) - AltTextLab is an AI service that generates accessible, SEO-aware alt text for images. It helps teams make image content easier to understand, index, and publish.
- [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization.
- [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications.
- [Apiframe](https://composio.dev/toolkits/apiframe) - Apiframe is an API platform for generating and managing AI images, videos, music, uploads, assets, jobs, and custom LoRAs. It gives developers one clean API for creative AI workflows without juggling multiple model providers.
- [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations.
- [Arize AX](https://composio.dev/toolkits/arize_ax) - Arize AX is an AI engineering platform for tracing, evaluating, and improving AI applications. Use it to debug LLM behavior, compare experiments, and improve production AI quality.
- [Artificial Analysis](https://composio.dev/toolkits/artificial_analysis) - Artificial Analysis is an independent benchmarking platform for AI models and API providers. Use it to compare model intelligence, coding, math, pricing, latency, throughput, and arena rankings.
- [AssemblyAI](https://composio.dev/toolkits/assemblyai) - AssemblyAI is a speech-to-text and audio intelligence API for uploaded or hosted media. Use it to turn audio and video into accurate transcripts, summaries, and insights.
- [Astica ai](https://composio.dev/toolkits/astica_ai) - Astica ai provides APIs for computer vision, NLP, and voice synthesis. Integrate advanced AI features into your app with a single API key.
- [Avoma](https://composio.dev/toolkits/avoma) - Avoma is an AI meeting assistant for recording, transcribing, analyzing, and managing meetings, calls, notes, scorecards, and conversation intelligence. It helps teams turn conversations into searchable notes, follow-ups, coaching insights, and revenue intelligence.
- [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient.
- [Bland AI](https://composio.dev/toolkits/bland_ai) - Bland AI is a conversational AI platform for building voice agents, phone calls, messaging, and communication workflows. Use it to automate calling, evaluate conversations, and run voice operations at scale.
- [Botbaba](https://composio.dev/toolkits/botbaba) - Botbaba is a platform for building, managing, and deploying conversational AI chatbots across messaging channels. It streamlines chatbot automation, making it easier to integrate AI into customer interactions.

## Frequently Asked Questions

### Do I need my own developer credentials to use Past.dev with Composio?

Yes, Past.dev requires you to configure your own API key. Once set up, Composio handles secure credential storage and API request handling for you.

### Can I use multiple toolkits together?

Yes! Composio's Tool Router enables agents to use multiple toolkits. [Learn more](https://docs.composio.dev/tool-router/overview).

### Is Composio secure?

Composio is SOC 2 and ISO 27001 compliant with all data encrypted in transit and at rest. [Learn more](https://trust.composio.dev).

### What if the API changes?

Composio maintains and updates all toolkit integrations automatically, so your agents always work with the latest API versions.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)