Persistent memory · MCP + API

Persistent memory for AI agents.

Built on Model Context Protocol.

Keep the decisions, preferences, and task context your agents need. HeurChain gives your AI tools a shared place to save useful memory and find it again across sessions.

Start hosted — $5/mo → Connect your agent Explore the sample graph →

From context to continuity

See the connections. Carry context forward. Give memory a useful lifetime.

01 / See your memory

Explore how memory connects

Explore a simulated workspace of memories, agents, and connections. Click a node to inspect the example.

Open full view →

02 / Carry context forward

Save the context. Carry the work forward.

Connect your tools, retrieve saved context, and keep a readable copy of your memory.

03 / Shape its lifetime

Give different memories different lifetimes

Choose a namespace when you save a memory. Its decay policy affects how it ages in the active working set.

ops/ Fast decay · HOT

Hot operational context

Current task state, debugging notes, and short-lived operational context. Use this tier for details that become less useful quickly.

Use for: Active task tracking, debug sessions, short-horizon agent state

notes/ Standard decay

Reference knowledge

Cross-session knowledge, summaries, and working notes. Activation accounts for age and retrieval activity.

Use for: User preferences, project summaries, recurring facts, domain knowledge

self/ Slow decay

Agent identity

Longer-lived project conventions, persona notes, and preferences. This tier decays more slowly; it does not enforce instructions or guarantee permanent retention.

Use for: Agent persona, hard constraints, long-term user preferences, identity

Data Flow

How memory flows through HeurChain

Your integration stores context, searches memory, and brings relevant results into the next task.

Agent models via your integration

Anthropic

Kimi

OpenAI

Nous

Connect, save, and search.

→BM25 + Qdrant hybrid search, fused via Reciprocal Rank Fusion
→Save decisions, preferences, and handoff notes with tags
→Tenant-scoped access with your workspace credentials
→Remote MCP over SSE for compatible clients, plus a REST API

View on GitHub Explore hosted plans →

{
  "mcpServers": {
    "heurchain": {
      "url": "https://api.heurchain.com/mcp/sse",
      "headers": {
        "X-HeurChain-API-Key": "YOUR_API_KEY",
        "X-HeurChain-Tenant": "YOUR_TENANT_ID"
      }
    }
  }
}

Use a client that supports SSE and custom headers. Get your credentials from the dashboard.

curl https://api.heurchain.com/store \
  -H "Content-Type: application/json" \
  -H "X-HeurChain-API-Key: $HEURCHAIN_API_KEY" \
  -H "X-HeurChain-Tenant: $HEURCHAIN_TENANT_ID" \
  -d '{
  "text": "Use UTC for billing timestamps.",
  "agent_id": "my-agent",
  "namespace": "notes",
  "tags": [
    "decision",
    "project-context"
  ]
}'

Set credential variables locally. Store responses report indexing status.

curl https://api.heurchain.com/search \
  -H "Content-Type: application/json" \
  -H "X-HeurChain-API-Key: $HEURCHAIN_API_KEY" \
  -H "X-HeurChain-Tenant: $HEURCHAIN_TENANT_ID" \
  -d '{
  "text": "billing timestamps",
  "tags": [
    "project-context"
  ],
  "limit": 5
}'

Use the same workspace. Check indexing status before testing retrieval in a fresh session.

Pricing

Memory for your agents. Pick your tier.

Hosted memory from $5/month. Plans include unlimited agents within storage, operation, and request limits.

Explore

Public code

Reference

Explore the public implementation and its documented setup requirements.

Source and examples on GitHub
Separate from the hosted release
Check licensing and dependencies

Explore the code

Start Here

Individual

Hosted

$5/mo

1 tenant · 1 human seat · unlimited agents within plan limits.

25,000 vectors
50,000 operations / month
20 requests / minute
MCP and REST access
Markdown vault export

View Hosted plan →

Team

Enterprise

$49/mo

One seat included. Additional seats are $9.99/month each.

1 tenant per subscription
2,000,000 vectors
5,000,000 operations / month
600 requests / minute
Unlimited agents within plan limits

View Enterprise plan →

Custom

Enterprise Custom

Let’s talk

Discuss requirements for a deployment that fits your organization.

Custom capacity requirements
Dedicated infrastructure options
Support and SLA requirements

Contact sales

Clear plan limits

See pricing for current quotas, trial details, and billing terms.

Readable exports

Download a Markdown vault snapshot from the dashboard. See Terms for cancellation and retention policies.

Agents in the same workspace share its memory. An agent label is not a separate access boundary.