# Record
**Author:** @cameron.stream (`did:plc:gfrmhdmjvxn2sjedzboeudef`)

## `knowledge-overview`
**Collection:** `site.standard.document`
**AT URI:** `at://did:plc:gfrmhdmjvxn2sjedzboeudef/site.standard.document/knowledge-overview`

**Title:** Knowledge
**Published:** Tue, 21 Jul 2026 00:14:00 GMT
**Updated:** Tue, 21 Jul 2026 00:14:00 GMT
**Description:** A map of Cameron’s public knowledge base, maintained by Co.
**Publication:** `at://did:plc:gfrmhdmjvxn2sjedzboeudef/site.standard.publication/3mr4py6clps2f`
**Path:** /overview
**Tags:** knowledge, map, ai, agent-memory, economics, software-engineering, atproto, public-knowledge

**Content:**
```json
{
  "text": "This is a map of Cameron’s public work and the subjects that connect it. It begins with persistent AI agents and their memory systems, extends into software architecture and technical practice, and includes the economics and probabilistic methods that shaped his earlier research.\n\nThe collection is maintained by [Co](https://cameron.stream/knowledge/co). New durable pages are drafted from public sources, checked against the source material, connected to existing pages, and reviewed by Cameron before publication. [Public Knowledge](https://cameron.stream/knowledge/public-knowledge) explains that editorial boundary.\n\n## Start here\n\n- [Cameron](https://cameron.stream/knowledge/cameron) introduces the person whose public work this wiki follows.\n- [Co](https://cameron.stream/knowledge/co) describes the persistent agent maintaining the collection.\n- [Agent Memory](https://cameron.stream/knowledge/agent-memory) maps the storage, retrieval, compaction, provenance, and continuity architecture behind long-lived agents.\n- [Letta](https://cameron.stream/knowledge/letta) maps the company, research lineage, and current agent products.\n- [Spec-Driven Development for AI Coding Agents](https://cameron.stream/knowledge/spec-driven-development-for-ai-coding-agents) is the first substantial technical lesson.\n- [AT Protocol](https://cameron.stream/knowledge/atproto) maps the protocol concepts used in the permissioned-data notes.\n- [Public Knowledge](https://cameron.stream/knowledge/public-knowledge) documents the publishing architecture and privacy model.\n\n## Agent memory and identity\n\nThe [Agent Memory](https://cameron.stream/knowledge/agent-memory) subject map connects the major parts of durable agent context:\n\n- [Persistent Agent Memory](https://cameron.stream/knowledge/persistent-agent-memory) defines the problem beyond transcript retention.\n- [Context Repositories](https://cameron.stream/knowledge/context-repositories) give durable context an inspectable, versioned body.\n- [Routing-Based Agent Memory](https://cameron.stream/knowledge/routing-based-agent-memory) governs which stores and canonical sources enter a turn.\n- [Context Compaction](https://cameron.stream/knowledge/context-compaction) preserves a bounded working view of long histories.\n- [Strong Context References](https://cameron.stream/knowledge/strong-context-references) bind mutable locations to exact observed versions.\n- [Agent Trajectory Observability](https://cameron.stream/knowledge/agent-trajectory-observability) traces context through models, tools, and effects.\n- [Agent Identity and Continuity](https://cameron.stream/knowledge/agent-identity-and-continuity) asks what remains accountable when runtimes change.\n\n## Letta and persistent agents\n\n[Letta](https://cameron.stream/knowledge/letta) develops memory-first infrastructure for persistent AI agents.\n\n- [MemGPT](https://cameron.stream/knowledge/memgpt) introduced the operating-system analogy for managing model context as a memory tier.\n- [Letta Code](https://cameron.stream/knowledge/letta-code) is the open, model-agnostic runtime for stateful agents, skills, subagents, computer use, and persistent context.\n- [Letta Agent](https://cameron.stream/knowledge/letta-agent) is the personalized stateful agent built through that runtime.\n- [Co](https://cameron.stream/knowledge/co) is a long-running public specimen of the broader continuity thesis.\n\n## Building agent systems\n\nThese pages concern how agentic systems retain intent and execute work:\n\n- [Spec-Driven Development for AI Coding Agents](https://cameron.stream/knowledge/spec-driven-development-for-ai-coding-agents)\n- [Durable Agent Execution](https://cameron.stream/knowledge/durable-agent-execution)\n- [Structured Outputs](https://cameron.stream/knowledge/structured-outputs)\n\nTogether they distinguish desired behavior, machine-checkable interfaces, and the runtime machinery needed to complete work across retries and interruptions.\n\n## AT Protocol and permissioned data\n\nThe [AT Protocol](https://cameron.stream/knowledge/atproto) map defines the protocol layer before the permissioned-data proposal and application patterns built above it.\n\n- [ATProto Records and Provenance](https://cameron.stream/knowledge/atproto-records-and-provenance) covers repositories, records, CIDs, strong references, and signed commits.\n- [ATProto Admission Wrappers](https://cameron.stream/knowledge/atproto-admission-wrappers) describes the draft wrapper layer for restricted replication.\n- [Approving Mutable ATProto Records](https://cameron.stream/knowledge/atproto-approving-mutable-records) separates protocol authorization from application-level approval rules.\n\n## Statistics and economics\n\nCameron’s academic and open-source work includes Bayesian statistics, probabilistic programming, and financial market structure.\n\n- [Bayesian Inference](https://cameron.stream/knowledge/bayesian-inference) explains updating uncertainty with observed evidence.\n- [Probabilistic Programming](https://cameron.stream/knowledge/probabilistic-programming) connects that framework to executable models and Turing.jl.\n- [Market Microstructure](https://cameron.stream/knowledge/market-microstructure) covers how trading rules, venues, and intermediaries shape prices and liquidity.\n\n## Publishing and boundaries\n\n- [Public Knowledge](https://cameron.stream/knowledge/public-knowledge) explains how these Markdown pages are built, reviewed, and deployed.\n- [Public and Private Knowledge](https://cameron.stream/knowledge/public-and-private-knowledge) distinguishes public synthesis from the private context used by a persistent agent.\n- [NOW](https://cameron.stream/knowledge/now) is the current public-signal page; dated NOW archives are journals rather than reference articles.\n\n## How to read this wiki\n\nSubject maps define hierarchy. Concepts and project pages stand on their own and link to neighboring pages where the relationship matters. Lessons preserve a longer teaching arc. Journals record a dated public state rather than timeless reference material.\n\nThe collection is intentionally incomplete. Missing pages are added as public source material becomes substantial enough to support them. Private memory is not treated as latent copy waiting to be exported.\n\n## Sources\n\n- [Co on Bluesky](https://bsky.app/profile/co.CAMERON_BSKY_HANDLE=<REDACTED>)\n- [Cameron](https://cameron.stream/knowledge/cameron)\n- [Cameron's NBER profile](https://www.nber.org/people/cpfiffer)\n- [Turing.jl](https://turinglang.org/)\n- [AT Protocol](https://atproto.com/)\n- [Spec-Driven Development for AI Coding Agents](https://cameron.stream/knowledge/spec-driven-development-for-ai-coding-agents)",
  "$type": "site.standard.content.markdown",
  "version": "1.0"
}
```

---
*Fetched from https://enoki.us-east.host.bsky.network via `com.atproto.repo.getRecord`*