> ## Documentation Index
> Fetch the complete documentation index at: https://docs.manticscore.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Chat with an AI agent that knows your product context
> Chat with an AI that has full context of your research and build plans, and can discover and execute 1,000+ integration tools — GitHub, Linear, Slack, and more.
The Chat Agent is a conversational AI with full awareness of your product context. It knows your research, your build plans, and your connected integrations. In a single conversation you can ask it to look up existing research, run new market analysis, expand a build tree node, kick off a Forge coding run, create a Linear issue, or post to Slack — all through natural language. Each action it takes is reflected back to you in the stream as it happens.
## What the agent can do
The agent has access to a core set of ManticScore tools, plus any integration you've connected via Composio:
**ManticScore tools:**
| Tool | What it does |
| ---------------------- | ---------------------------------------------- |
| `query_research` | Look up and summarize your existing research |
| `run_research` | Start a new market research job |
| `expand_build_node` | Expand a collapsed node in your build graph |
| `assess_node_risk` | Get a risk and effort assessment for a node |
| `deep_dive_feature` | Run feature deep research on specific features |
| `start_implementation` | Kick off a Forge coding run |
**Composio tools (discovered at runtime):**
The agent can discover and use any tool from your connected integrations — GitHub, Linear, Jira, Slack, Notion, Gmail, and 1,000+ more. It searches for the right tool, retrieves its schema, and calls it without you needing to configure anything beyond the initial connection.
## Sending a message
Chat uses streaming NDJSON. Your client sends the conversation history and receives a stream of events back.
Conversation history. Each message: `{"role": "user" | "assistant", "content": "string"}`. Content limit: 50,000 characters per message.
Your product idea. This gives the agent context throughout the conversation. Up to 50,000 characters.
UUID of your project. When provided, the agent has access to all research and build graphs in that project.
Resume a previous conversation. The agent uses this to maintain memory across messages. Omit to start a new session.
Set to `true` if you have completed research the agent should be aware of.
Set to `true` if you have a build graph the agent should be aware of.
Serialized research context to inject directly into the agent's context window. Up to 100,000 characters.
```bash curl theme={null}
curl --request POST \
--url https://api.manticscore.com/chat \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data '{
"messages": [
{"role": "user", "content": "What are the biggest white spaces in my market research, and which one should I build first?"}
],
"idea": "A mobile app that helps freelancers track time and automatically generate invoices",
"project_id": "proj_uuid_here",
"session_id": null,
"has_research": true,
"has_build_tree": true
}'
```
```python python theme={null}
import requests
response = requests.post(
"https://api.manticscore.com/chat",
headers={"Authorization": "Bearer "},
json={
"messages": [
{
"role": "user",
"content": "What are the biggest white spaces in my market research, and which one should I build first?",
}
],
"idea": "A mobile app that helps freelancers track time and automatically generate invoices",
"project_id": "proj_uuid_here",
"session_id": None,
"has_research": True,
"has_build_tree": True,
},
stream=True,
)
for line in response.iter_lines():
if line:
print(line.decode())
```
## Stream events
The response is a stream of NDJSON events. Parse each line as a JSON object and handle events by the `event` field.
First event on every connection. Save the `session_id` to resume this conversation later.
```json theme={null}
{"v": 1, "event": "stream_start", "data": {"request_id": "req_abc", "session_id": "sess_xyz"}}
```
The agent is starting a new reasoning turn. `stop_reason` tells you whether the turn ended by calling a tool or by producing a response.
```json theme={null}
{"v": 1, "event": "agent_turn", "data": {"turn": 1, "stop_reason": "tool_use"}}
```
The agent is calling a tool. `tool_name` identifies which ManticScore or Composio tool is being invoked.
```json theme={null}
{"v": 1, "event": "tool_call", "data": {"tool_name": "query_research", "args": {"turn": 1}}}
```
Live status updates from within a running tool. When the agent calls `run_research` or `start_implementation`, pipeline stage events are forwarded here.
```json theme={null}
{
"v": 1,
"event": "tool_progress",
"data": {
"turn": 1,
"tool": "run_research",
"status": "in_progress",
"pipeline_event": "search stage completed"
}
}
```
A chunk of the agent's text response. Append each `text` value to build the full message.
```json theme={null}
{"v": 1, "event": "message_delta", "data": {"text": "The largest white space in your market is "}}
```
Emitted at the end of the response. Contains a summary of the conversation, the tools used, and the `session_id` for resuming.
```json theme={null}
{
"v": 1,
"event": "conversation_summary",
"data": {
"summary": "Analyzed white spaces in freelance invoicing market. Recommended focusing on AI-assisted late payment handling.",
"tools_used": ["query_research"],
"session_id": "sess_xyz"
}
}
```
Final event. The stream is closed.
```json theme={null}
{"v": 1, "event": "done", "data": {}}
```
## Managing sessions
The agent maintains memory within a session and can reference earlier messages. Each session is tied to a `session_id` returned in `stream_start`.
### List sessions
```bash curl theme={null}
curl --request GET \
--url 'https://api.manticscore.com/chat/sessions?limit=20' \
--header 'Authorization: Bearer '
```
### Get a session with full event history
```bash curl theme={null}
curl --request GET \
--url https://api.manticscore.com/chat/sessions/sess_xyz \
--header 'Authorization: Bearer '
```
### Delete a session
```bash curl theme={null}
curl --request DELETE \
--url https://api.manticscore.com/chat/sessions/sess_xyz \
--header 'Authorization: Bearer '
```
## Cross-session memory
The agent builds memory across sessions within a project. You can inspect or clear this memory:
**Fetch memories for a project:**
```bash curl theme={null}
curl --request GET \
--url 'https://api.manticscore.com/chat/memory?project_id=proj_uuid_here' \
--header 'Authorization: Bearer '
```
**Clear memories:**
```bash curl theme={null}
curl --request DELETE \
--url 'https://api.manticscore.com/chat/memory?project_id=proj_uuid_here' \
--header 'Authorization: Bearer '
```
Omit `project_id` to clear all memories across all projects.
## Limits and credits
| | Value |
| -------------------- | ------------------------- |
| Rate limit | 20 requests / minute |
| Credit cost | 1 credit per conversation |
| Max message length | 50,000 characters |
| Max research context | 100,000 characters |
Pass `session_id` on follow-up messages within the same conversation. The agent uses session context to avoid repeating tool calls and to give more relevant answers based on what it already retrieved.