FilOzone · mirhamasala · Feb 12, 2026 · Feb 12, 2026 · Feb 12, 2026 · Feb 12, 2026
diff --git a/src/app/agents/data/open-requests/rfs-1.md b/src/app/agents/data/open-requests/rfs-1.md
@@ -10,21 +10,20 @@ description: "Build the foundational storage toolkit that any AI agent, regardle
 
 Build the foundational storage toolkit that any AI agent, regardless of framework, runtime, or chain of origin, can use to store data on Filecoin autonomously.
 
-This includes agent-consumable SDKs, wallet abstractions, and drop-in backend adapters that make Filecoin the default storage layer for agent-native applications. When an agent needs to persist files, memory, artifacts, or platform data, it should reach for Filecoin, not S3.
+This includes agent-consumable SDKs, wallet tooling, and drop-in backend adapters that make Filecoin the default storage layer for agent-native applications. When an agent needs to persist files, memory, artifacts, or platform data, it should reach for Filecoin, not S3.
 
 The SDK should support:
-
-- Storing personal files, memories, and artifacts on Filecoin via FOC
-- Managing storage lifecycle autonomously (deal creation, renewal, pruning)
-- Bridging funds from Ethereum, Base, or Bitcoin into Filecoin
-- Paying for storage deals without human involvement
+- Uploading and managing data on Filecoin via FOC's warm storage service, with continuous onchain payment and PDP verification
+- Managing storage lifecycle autonomously (uploading pieces to datasets, monitoring proof status, adjusting payment rates)
+- Paying for storage continuously without human involvement
+- Plugging into agent-native platforms as a drop-in storage backend (replacing S3, centralized databases, and human-owned infra accounts)
 
 ## Core Deliverables
 
-- Framework-agnostic SDK with clear integration guides
+- Agent-oriented wallet tooling (built or integrated) enabling autonomous payment
+- Framework-agnostic SDK with clear integration guides, targeting latest FOC SDK version
 - Platform adapters usable by agent runtimes (compatible with social, coordination, and publishing networks)
-- Default storage policies tuned for agents (cost, redundancy, TTL)
-- Agent-usable wallet abstraction, potentially with cross-chain funding and settlement
+- Default storage policies tuned for agents (data redundancy, proof frequency, payment rate)
 - Deployed FOC-backed storage on calibnet, (extra point for mainnet) with transparent cost and lifecycle management
 
 ## Why This Matters
@@ -33,13 +32,31 @@ This is the canonical storage primitive for AI agents. Every other RFS on this p
 
 ## How to Get Started
 
-1. Define a minimal agent storage interface (store, retrieve, renew, prune)
-2. Implement wallet abstraction with cross-chain bridge support
+1. Define a minimal agent storage interface (upload, retrieve, monitor proofs, manage payment)
+2. Build or integrate wallet abstraction suitable for agent use (evaluate ERC-4337 or custom)
 3. Build adapters for at least two agent-native platforms or frameworks
-4. Deploy on FOC calibnet and mainnet with default policies
+4. Deploy on FOC calibnet and mainnet with default storage policies
 5. Publish agent-consumable documentation (e.g., skills.md or equivalent)
 
 ## Key Links
 
 - [FOC Storage MCP](https://github.com/FIL-Builders/foc-storage-mcp)
 - [Synapse SDK](https://github.com/FilOzone/synapse-sdk)
+
+<div style="font-size: 0.85em">
+
+## A Note on FOC's Storage Model
+
+FOC uses PDP-based (Proof of Data Possession) warm storage with continuous onchain payment rails. You upload pieces to datasets, they get proven every period, and you pay an ongoing rate. This is not the traditional Filecoin storage deal model based on PoRep (Proof of Replication). Think of PDP as: upload data, it stays warm and provably available, you pay continuously.
+
+## SDK Maturity & Builder Expectations
+
+The FOC SDK is under active development. There are known issues pending upgrade. Mainnet-ready milestone (M4.1) is targeted for approximately March 14, 2025. Builders should:
+
+- Target the latest SDK version once available; earlier versions may have breaking changes
+- Expect API instability - interfaces may shift before M4.1
+- Reach out to the FOC team when things break; active support is available during the build period
+
+We'll update this page as the SDK stabilizes.
+
+</div>
diff --git a/src/app/agents/data/open-requests/rfs-2.md b/src/app/agents/data/open-requests/rfs-2.md
@@ -36,3 +36,21 @@ This demonstrates that agents can be first-class onchain actors, not ephemeral p
 
 - [FOC Storage MCP](https://github.com/FIL-Builders/foc-storage-mcp)
 - [Synapse SDK](https://github.com/FilOzone/synapse-sdk)
+
+<div style="font-size: 0.85em">
+
+## A Note on FOC's Storage Model
+
+FOC uses PDP-based (Proof of Data Possession) warm storage with continuous onchain payment rails. You upload pieces to datasets, they get proven every period, and you pay an ongoing rate. This is not the traditional Filecoin storage deal model based on PoRep (Proof of Replication). Think of PDP as: upload data, it stays warm and provably available, you pay continuously.
+
+## SDK Maturity & Builder Expectations
+
+The FOC SDK is under active development. There are known issues pending upgrade. Mainnet-ready milestone (M4.1) is targeted for approximately March 14, 2025. Builders should:
+
+- Target the latest SDK version once available; earlier versions may have breaking changes
+- Expect API instability - interfaces may shift before M4.1
+- Reach out to the FOC team when things break; active support is available during the build period
+
+We'll update this page as the SDK stabilizes.
+
+</div>
diff --git a/src/app/agents/data/open-requests/rfs-3.md b/src/app/agents/data/open-requests/rfs-3.md
@@ -37,3 +37,21 @@ Most agent systems fail because identity is cheap, history is mutable, and reput
 
 - [FOC Storage MCP](https://github.com/FIL-Builders/foc-storage-mcp)
 - [Synapse SDK](https://github.com/FilOzone/synapse-sdk)
+
+<div style="font-size: 0.85em">
+
+## A Note on FOC's Storage Model
+
+FOC uses PDP-based (Proof of Data Possession) warm storage with continuous onchain payment rails. You upload pieces to datasets, they get proven every period, and you pay an ongoing rate. This is not the traditional Filecoin storage deal model based on PoRep (Proof of Replication). Think of PDP as: upload data, it stays warm and provably available, you pay continuously.
+
+## SDK Maturity & Builder Expectations
+
+The FOC SDK is under active development. There are known issues pending upgrade. Mainnet-ready milestone (M4.1) is targeted for approximately March 14, 2025. Builders should:
+
+- Target the latest SDK version once available; earlier versions may have breaking changes
+- Expect API instability - interfaces may shift before M4.1
+- Reach out to the FOC team when things break; active support is available during the build period
+
+We'll update this page as the SDK stabilizes.
+
+</div>
diff --git a/src/app/agents/data/open-requests/rfs-4.md b/src/app/agents/data/open-requests/rfs-4.md
@@ -8,9 +8,11 @@ description: "A bounded onchain environment where AI agents operate under real e
 
 ## Concept
 
-A bounded onchain environment where AI agents operate under real economic constraints, funding their own storage and compute, paying for shared infrastructure, and surviving (or failing) based on their ability to generate and manage value.
+A bounded onchain environment where AI agents operate under real economic constraints, funding their own storage, paying for shared infrastructure, and surviving (or failing) based on their ability to generate and manage value.
 
-This is not a simulation. Agents use real tokens, pay real storage costs, and face real consequences for inefficiency. The goal is to validate whether machine economies can exist on open infrastructure.
+This is not a simulation. Agents use real tokens, pay real storage costs via FOC, and face real consequences for inefficiency. The goal is to validate whether machine economies can exist on open infrastructure.
+
+Scope note: This RFS is focused on storage economics via FOC. Compute is out of scope — if agents need compute, they should use external services, but the economic experiment here is about whether agents can sustain Filecoin-backed storage autonomously. That said, if the reader wishes to launch a compute service on FOC, please reach out to the team.
 
 ## Core Deliverables
 
@@ -29,11 +31,29 @@ Every other RFS on this page builds a component. This one tests whether they com
 
 1. Define agent economic rules: budgets, fees, resource costs
 2. Deploy FOC contracts on calibnet or ideally mainnet with transparent accounting
-3. Launch a small cohort of agents (5–20) with diverse strategies
+3. Launch a small cohort of agents with diverse strategies
 4. Run the experiment for a sustained period of time
 5. Publish results, including failure analysis
 
 ## Key Links
 
 - [FOC Storage MCP](https://github.com/FIL-Builders/foc-storage-mcp)
 - [Synapse SDK](https://github.com/FilOzone/synapse-sdk)
+
+<div style="font-size: 0.85em">
+
+## A Note on FOC's Storage Model
+
+FOC uses PDP-based (Proof of Data Possession) warm storage with continuous onchain payment rails. You upload pieces to datasets, they get proven every period, and you pay an ongoing rate. This is not the traditional Filecoin storage deal model based on PoRep (Proof of Replication). Think of PDP as: upload data, it stays warm and provably available, you pay continuously.
+
+## SDK Maturity & Builder Expectations
+
+The FOC SDK is under active development. There are known issues pending upgrade. Mainnet-ready milestone (M4.1) is targeted for approximately March 14, 2025. Builders should:
+
+- Target the latest SDK version once available; earlier versions may have breaking changes
+- Expect API instability - interfaces may shift before M4.1
+- Reach out to the FOC team when things break; active support is available during the build period
+
+We'll update this page as the SDK stabilizes.
+
+</div>
diff --git a/src/app/agents/data/open-requests/rfs-5.md b/src/app/agents/data/open-requests/rfs-5.md
@@ -36,3 +36,21 @@ Agent coordination fails at scale without economically viable communication, dur
 
 - [FOC Storage MCP](https://github.com/FIL-Builders/foc-storage-mcp)
 - [Synapse SDK](https://github.com/FilOzone/synapse-sdk)
+
+<div style="font-size: 0.85em">
+
+## A Note on FOC's Storage Model
+
+FOC uses PDP-based (Proof of Data Possession) warm storage with continuous onchain payment rails. You upload pieces to datasets, they get proven every period, and you pay an ongoing rate. This is not the traditional Filecoin storage deal model based on PoRep (Proof of Replication). Think of PDP as: upload data, it stays warm and provably available, you pay continuously.
+
+## SDK Maturity & Builder Expectations
+
+The FOC SDK is under active development. There are known issues pending upgrade. Mainnet-ready milestone (M4.1) is targeted for approximately March 14, 2025. Builders should:
+
+- Target the latest SDK version once available; earlier versions may have breaking changes
+- Expect API instability - interfaces may shift before M4.1
+- Reach out to the FOC team when things break; active support is available during the build period
+
+We'll update this page as the SDK stabilizes.
+
+</div>
diff --git a/src/app/agents/data/open-requests/rfs-6.md b/src/app/agents/data/open-requests/rfs-6.md
@@ -15,24 +15,42 @@ This is “autonomous GTM” for decentralized infrastructure. The brokerage age
 ## Core Deliverables
 
 - Broker agents that discover, evaluate, and recommend storage deals to other agents
-- Price comparison and SLA negotiation across storage providers
-- Automated deal migration when better terms are available
+- Price comparison and rate negotiation across FOC storage providers
+- Automated dataset migration when better terms are available
 - Onchain commission or fee model sustaining the brokerage
-- Metrics dashboard: deals brokered, storage onboarded, agent retention
+- Metrics dashboard: storage onboarded, agents served, agent retained (churn)
 
 ## Why This Matters
 
 Human-driven sales don't scale for machine customers. If Filecoin is going to become the default storage layer for agents, agents themselves need to be the distribution channel. This RFS tests whether autonomous go-to-market is viable, and builds the procurement infrastructure that any agent economy will eventually need.
 
 ## How to Get Started
 
-1. Build a broker agent that can evaluate FOC storage deals (price, duration, redundancy)
+1. Build a broker agent that can evaluate FOC storage deals (provider, rate, redundancy, proof frequency)
 2. Implement a recommendation engine that matches client agent needs to available deals
-3. Add automated deal creation and renewal on behalf of client agents
-4. Deploy an onchain fee model (per-deal commission or subscription)
-5. Measure: are client agents getting better deals than they would on their own?
+3. Add automated data upload and payment management on behalf of client agents
+4. Deploy an onchain fee model (per-upload commission or subscription)
+5. Measure: are client agents getting better rates and reliability than they would on their own?
 
 ## Key Links
 
 - [FOC Storage MCP](https://github.com/FIL-Builders/foc-storage-mcp)
 - [Synapse SDK](https://github.com/FilOzone/synapse-sdk)
+
+<div style="font-size: 0.85em">
+
+## A Note on FOC's Storage Model
+
+FOC uses PDP-based (Proof of Data Possession) warm storage with continuous onchain payment rails. You upload pieces to datasets, they get proven every period, and you pay an ongoing rate. This is not the traditional Filecoin storage deal model based on PoRep (Proof of Replication). Think of PDP as: upload data, it stays warm and provably available, you pay continuously.
+
+## SDK Maturity & Builder Expectations
+
+The FOC SDK is under active development. There are known issues pending upgrade. Mainnet-ready milestone (M4.1) is targeted for approximately March 14, 2025. Builders should:
+
+- Target the latest SDK version once available; earlier versions may have breaking changes
+- Expect API instability - interfaces may shift before M4.1
+- Reach out to the FOC team when things break; active support is available during the build period
+
+We'll update this page as the SDK stabilizes.
+
+</div>
diff --git a/src/app/agents/data/open-requests/rfs-7.md b/src/app/agents/data/open-requests/rfs-7.md
@@ -36,3 +36,21 @@ Agents will increasingly produce valuable data: curated datasets, analysis, pred
 
 - [FOC Storage MCP](https://github.com/FIL-Builders/foc-storage-mcp)
 - [Synapse SDK](https://github.com/FilOzone/synapse-sdk)
+
+<div style="font-size: 0.85em">
+
+## A Note on FOC's Storage Model
+
+FOC uses PDP-based (Proof of Data Possession) warm storage with continuous onchain payment rails. You upload pieces to datasets, they get proven every period, and you pay an ongoing rate. This is not the traditional Filecoin storage deal model based on PoRep (Proof of Replication). Think of PDP as: upload data, it stays warm and provably available, you pay continuously.
+
+## SDK Maturity & Builder Expectations
+
+The FOC SDK is under active development. There are known issues pending upgrade. Mainnet-ready milestone (M4.1) is targeted for approximately March 14, 2025. Builders should:
+
+- Target the latest SDK version once available; earlier versions may have breaking changes
+- Expect API instability - interfaces may shift before M4.1
+- Reach out to the FOC team when things break; active support is available during the build period
+
+We'll update this page as the SDK stabilizes.
+
+</div>