Turn data into shared, structured memory
Owletto gives all your agents the same durable graph: connectors, recall, and managed auth without leaking credentials to the runtime.
How it works
Turn scattered prompts, tools, and application data into a shared context layer your agents can use everywhere.
Model the venture landscape
Represent companies, founders, investors, and funding rounds as linked entities for deal tracking and pattern recognition.
Connect sources
Ingest from Crunchbase, LinkedIn, news sources, and internal deal memos through supported connectors and MCP proxying.
Company and deal memory comes from public databases, proprietary sources, and internal deal memos.
| Type | Source | Added context |
|---|---|---|
| Data providers | Company databases | Pull funding rounds, company descriptions, and team data from Crunchbase, PitchBook, or similar platforms. |
| Web scraping | Company websites | Monitor company blogs, engineering blogs, and job postings for growth and product signals. |
| News API | Press and announcements | Track funding announcements, leadership changes, and strategic moves from news and press releases. |
| Internal | Deal memos and notes | Import investment committee memos, sourcing notes, and partnership discussions for private context. |
Let users connect their data
Support OAuth for data providers, API keys for premium sources, and manual imports for proprietary deal information.
Connect data providers and internal tools while keeping credentials isolated from workers.
| Access | System | How it works |
|---|---|---|
| API key | Premium databases | Store Crunchbase API keys or PitchBook credentials centrally for company and funding data. |
| RSS | Company news feeds | Pull company blog RSS feeds, tech press, and announcement lists without per-request auth. |
| Web auth | Private portals | Authorize access to investor portals or private company databases for portfolio monitoring. |
| Agent boundary | Credential isolation | The VC agent receives extracted company insights, not raw database access. |
Reuse context everywhere
Investment intelligence powers deal review agents in internal tools, messaging apps, and MCP clients like OpenClaw, ChatGPT, and Claude.
The same company and deal memory powers investment workflows across the firm.
Keep it fresh
Watchers turn new funding rounds, portfolio updates, and market signals into current company memory.
A scheduled watcher keeps this memory current as new source changes arrive.
{ new_funding[], product_launches[], headcount_change, competitive_moves[], market_expansion[] }Latest blog posts
Filesystem vs Database for Agent Memory
Agents need a workspace to think in and a warehouse to remember in. The filesystem is for ephemeral work. The memory layer is for durable organizational knowledge.
Add OpenClaw to your Next.js app in 10 minutes
Embed OpenClaw agents in a Next.js project with per-user sandboxing, MCP tools, and network isolation — no Docker required.
MCP Is Overengineered, Skills Are Too Primitive
MCP HTTP is great for external services. MCP stdio is redundant. And most skill systems are just prompt text with no reproducibility. Here's what we built instead.
Beats other memory systems on public benchmarks
Apples-to-apples comparison on public memory datasets. Same answerer (glm-5.1) and same questions.
LongMemEval (oracle-50)
Single-session knowledge retention.
| System | Overall | Answer | Retrieval | Latency |
|---|---|---|---|---|
| Lobu | 87.1% | 78.0% | 100.0% | 237ms |
| Supermemory | 69.1% | 56.0% | 96.6% | 702ms |
| Mem0 | 65.7% | 54.0% | 85.3% | 753ms |
LoCoMo-50
Multi-session conversational memory.
| System | Overall | Answer | Retrieval | Latency |
|---|---|---|---|---|
| Lobu | 57.8% | 38.0% | 79.5% | 121ms |
| Mem0 | 41.5% | 28.0% | 66.9% | 606ms |
| Supermemory | 23.2% | 14.0% | 36.5% | 532ms |
Start building shared memory
Model the right entities, connect your sources, and keep long-term context available across every agent workflow.