Recalld
PulseGate's liveness check found it on 28 Sep 2026; it is registered on GitHub and has been in the index since 28 Sep 2026. How this is checked
Recalld is a hosted memory layer for AI agents that extracts, reconciles, and retrieves persistent facts from conversations and documents. Its API provides memory writing, curated recall, and raw search primitives for developers building agent applications.
Inferred · not functionally tested
Overview
6 featuresPurpose: Building persistent, relevant memory and retrieval for AI agents without maintaining custom vector and deduplication pipelines.
Inferred · not functionally tested
Audience: AI developers building agent applications
Inferred · not functionally tested
Functions: rag, data_extraction
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: unknown · Self-hosting: unknown
Recorded constraints: pricing: freemium · license: Proprietary · platforms: API, WEB · deployment: browser, cloud_managed, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: recalld.ai · github.com. These links do not verify the individual claims.
Recalld is a Memory & skills project. Inferred · not functionally tested: It focuses on building persistent, relevant memory and retrieval for AI agents without maintaining custom vector and deduplication pipelines. Inferred · not functionally tested: Recalld is a B2B product aimed at AI developers building agent applications. Basis unknown · not verified: Recalld follows a freemium model. Basis unknown · not verified: It runs on the web and API.
Recalld first shipped in 2024. Development happens publicly on GitHub with 1.2k stars. Inferred · not functionally tested: Key capabilities include persistent memory, fact extraction, and fact reconciliation. Inferred · not functionally tested: Catalogued interfaces include a public API and an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Persistent memory
- Fact extraction
- Fact reconciliation
- Hybrid retrieval
- Curated recall
- Raw vector search
Topics: Inferred · not functionally tested
Built with & integrations
- Cloudflare
- cf-ray header · cf-cache-status header
- google_gemini
- bgemini- in the HTML
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed28 Sep · 21:59 UTCRecalld – A memory layer for AI agents that returns only relevant facts seen via Hacker News firehose (Algolia)Source: Hacker News firehose (Algolia) · Open
Frequently asked questions about Recalld
- What does Recalld do?
- Inferred · not functionally tested: Recalld focuses on building persistent, relevant memory and retrieval for AI agents without maintaining custom vector and deduplication pipelines. It is catalogued under Memory & skills on PulseGate.
- Who should use Recalld?
- Inferred · not functionally tested: Recalld is a B2B product built for AI developers building agent applications.
- Is Recalld free?
- Basis unknown · not verified: Yes — there is a free tier, with paid plans for advanced use.
- What platforms does Recalld run on?
- Basis unknown · not verified: Recalld runs on the web and API.
- Is Recalld still active?
- PulseGate's liveness check found it on 28 Sep 2026.
- What are alternatives to Recalld?
- Similar projects tracked by PulseGate include Recall™, AgentRecall, and Recall.Recall™AgentRecallRecall
- How long has Recalld been around?
- Recalld first shipped in 2024.
- Is Recalld open source?
- Basis unknown · not verified: Recalld has a public GitHub repository.
Similar projects
Closest matches by what these projects do