Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
docs(research): add Honcho (Plastic Labs) to the 2026 landscape
AkitaOnRails76084d49c47c
diff --git a/docs/comparison.md b/docs/comparison.mdindex 5364143c..c6967a9b 100644--- a/docs/comparison.md+++ b/docs/comparison.md@@ -51,6 +51,7 @@ not). See [where we're behind](#where-were-behind-or-different-by-choice).|---|---|---|---|| Fact extractors | Mem0, LangMem | Cheap per-turn personalization | Atomic facts lose relational/causal context (see [TriMem](research-2026-landscape.md#4-research-developments-worth-knowing)); LLM-per-turn; not file-first || Hosted memory API (hybrid) | **Supermemory** | Chunk-RAG + LLM temporal fact-graph + per-user profiles in one query; managed connectors (Drive/Notion/GitHub), multimodal, metadata/tag query filters | Cloud-first (best features + extraction are paid/Cloudflare-hosted); LLM-required quality path; an opaque graph is the source of truth (not file-first, nothing to `grep`/diff); the MIT self-host binary drops the connectors and extraction models |+| User-modeling / theory-of-mind | **Honcho** (Plastic Labs) | Reasoning-derived model of what each "peer" knows/believes over time — personalizes around the *human* the agent serves | Different problem: it remembers the *user*, ai-memory remembers the *project*. Opaque Postgres, LLM-required (Deriver/Dreamer), multi-service stack; adjacent (shares MCP/plugin delivery) but not a coding-memory migration target || Temporal knowledge graph | Zep/Graphiti, Cognee | Bi-temporal "what was true vs believed when" | Needs a graph DB; heavier to self-host. ai-memory ships **bi-temporal-lite** on SQLite ([`temporal.md`](temporal.md)) + typed edges ([`typed-edges.md`](typed-edges.md)) for the useful part || Memory OS / self-editing | Letta, MemOS, MIRIX | Agent curates its own tiered memory | Token-expensive self-editing; Letta itself now concedes file-first ("Is a Filesystem All You Need?") || Hosted context database | **OpenViking** (ByteDance) | Progressive L0/L1/L2 loading; directory-scoped retrieval; broad integrations | LLM-**required** (VLM + embeddings); opaque swappable storage; AGPLv3 core + SaaS/enterprise weight |diff --git a/docs/competitive-parity.md b/docs/competitive-parity.mdindex c00b6a85..83fb7185 100644--- a/docs/competitive-parity.md+++ b/docs/competitive-parity.md@@ -56,14 +56,16 @@ None of the competitors below has more than one or two of these; none has all.| **Zep/Graphiti** (temporal KG) | **Yes** for self-hosting coders avoiding Neo4j+LLM (Community Edition is discontinued); **no** for enterprise graph-query/world-time | One binary on SQLite, zero-LLM, files, coding-harness native, a supported self-host | True bi-temporal (world vs observed time), Cypher/BFS graph queries, custom entity/edge types, `minRating` || **Mem0** | **Mostly no — different buyer** (app end-user personalization). Yes only if you (mis)used it as coding-session memory | Zero-LLM, per-repo, cross-harness, editable pages, no API spend | Mem0's SDK/integration ecosystem + managed cloud personalization || **Letta / MemOS** | **No** if you're building your agent *on* Letta; **yes** if you only wanted your existing coding agent to remember | Additive memory under your existing harness, zero-LLM, no runtime adoption | The ADE + agent-framework machinery (which you don't need unless building on Letta) |-| **Mem0/Zep for apps; OpenViking, Supermemory** | different buyer (app/user personalization, hosted context DB) — **not migration targets** | — | — |+| **Honcho** (Plastic Labs) | **No — different problem.** It models the *human* (theory-of-mind peer representations); we remember the *project* | If you (mis)used it for coding continuity: file-first git truth, zero-LLM, single-binary self-host, per-project scoping, no mandatory LLM egress | Its user-psychology reasoning engine (Deriver/Dreamer/Dialectic), published user-recall benchmarks, managed cloud — none of which a coding-memory user needs |+| **Mem0/Zep for apps; OpenViking, Supermemory, Honcho** | different buyer (app/user personalization, hosted context DB, user-modeling) — **not migration targets** | — | — |Net: the premise holds where it should. For a **self-hosted, multi-harness,team, zero-LLM, data-ownership** coding-memory use case, ai-memory does the basicsand adds a moat none of them fully have — migration is justified. It does *not*-hold for app/user personalization (Mem0/Supermemory), enterprise graph queries-(Zep Cloud), agent-building runtimes (Letta), or a solo dev happy with Claude's-built-in — those are different buyers, and we should say so rather than overclaim.+hold for app/user personalization (Mem0/Supermemory), user-modeling /+theory-of-mind (Honcho), enterprise graph queries (Zep Cloud), agent-building+runtimes (Letta), or a solo dev happy with Claude's built-in — those are+different buyers, and we should say so rather than overclaim.## Did we copy without improving? — the borrowed-ideas audit@@ -124,7 +126,12 @@ implemented without a separate decision.** Ordered by leverage.(basic-memory's `build_context`/`memory://`, borrowed-but-unshipped); MCP toolbehavior hints (readOnly/destructive/idempotent) on the 23-tool surface; aclustering/dedup consolidation pass (mcp-memory-service's DBSCAN); a read-only- graph visualization in `/web`; a first-class TS SDK story for ecosystem parity.+ graph visualization in `/web`; a first-class TS SDK story for ecosystem parity;+ an optional **dialectic/oracle query** (ask-a-question → synthesized answer)+ and a **reasoning-tier knob** (Honcho) — but strictly as opt-in LLM layers+ *over* the zero-LLM FTS/RRF core, never a requirement. Deliberately out of+ scope: Honcho's theory-of-mind user-modeling engine (off-mission for coding+ memory; the global-scope preferences page already covers the useful slice).7. **Fix doc staleness the audit surfaced** (accuracy, not features):`research-basic-memory.md` understates basic-memory's shipped cross-encoderreranking + Teams tier; `research-agentmemory.md` says 53 tools / 124 endpointsdiff --git a/docs/research-2026-landscape.md b/docs/research-2026-landscape.mdindex fae94107..52963a61 100644--- a/docs/research-2026-landscape.md+++ b/docs/research-2026-landscape.md@@ -77,6 +77,7 @@ The market has consolidated into recognizable camps:| Memory OS / self-editing | **Letta**, MemOS, EverMemOS, MIRIX | The agent edits its own tiered memory via tools; "sleep-time compute" does consolidation off the hot path || Fact extractors | **Mem0**, LangMem | LLM extracts atomic facts per turn; lightweight personalization || Hosted memory API (hybrid) | **Supermemory** | Chunk-RAG + LLM temporal fact-graph + per-user profiles, answered in one query; managed connectors + multimodal; cloud-first (see below) |+| User-modeling / theory-of-mind | **Honcho** (Plastic Labs) | Memory as a *reasoning* problem: derive what each "peer" knows/believes about another over time; model the human, not the project (see below) || **File-first wiki memory** | **us**, basic-memory, OKF, Letta's filesystem result, mempalace (nominally) | Markdown source of truth, derived indexes, human-editable || Code intelligence | **DeusData/codebase-memory-mcp** (~42K stars) | Index the *codebase* (162 languages, tree-sitter → SQLite graph, static C binary) rather than the *session* - adjacent, not competing: it remembers what the code is, not what you did (see `research-codebase-memory-mcp.md`) || Agent-harness OS | **ECC** (~247K stars), plus the skills/agents-pack ecosystem | Install a whole plan→test→implement→review→**remember**→improve loop into the agent; memory is one thin pillar ("optimize the context window, persist everything else"), deliberately kept as *context, not policy* - adjacent, not competing (see `research-ecc.md`) |@@ -207,6 +208,50 @@ accuracy / latency / context-tokens "MemScore" triple are open and worthborrowing (see R8). Per the research-doc convention, Supermemory has nostandalone deep-dive; this section is its record.+**Adjacent, not head-to-head: `plastic-labs/honcho`** (~7K stars, AGPL-3.0+core + managed cloud, **$5.35M pre-seed** led by Variant/White Star/Betaworks).+Honcho is the archetype of a **new camp** this report had no bucket for:+**user-modeling / theory-of-mind memory**. Its unit of memory is a **"peer"**+(any entity that "persists but changes over time — users, agents, objects") and+its differentiator is treating memory as **"a reasoning problem, not a retrieval+problem"** — it models *what one peer knows and believes about another* over+time. The substrate is the opposite of ours on every axis we chose:+**PostgreSQL is the source of truth** (Postgres FTS/GIN + HNSW vectors, Redis+cache, pluggable LanceDB/Turbopuffer — **no git, no markdown, nothing to `grep`+or diff**), it is **LLM-required** (a **Deriver** does one structured-output LLM+call per message batch; a scheduled **Dreamer** runs surprisal-prioritized+"dream-time" consolidation into premise→conclusion reasoning trees — no zero-LLM+path), and it runs as a **multi-service stack** (FastAPI API + async worker ++Postgres + Redis), cloud-leaning with a self-hostable core. Its flagship is the+**Dialectic endpoint** (`peer.chat()`): a natural-language *oracle* — you ask a+question about a peer and a synchronous tool-using agent (`search_memory`,+`grep_messages`, `get_reasoning_chain`, temporal search, five reasoning tiers)+synthesizes an answer rather than returning raw hits. Benchmarks are strong but+**vendor self-reported** (blog dated Dec 19 2025): LongMemEval-S 90.4% (Haiku+4.5) / 92.6% (Gemini 3 Pro), LoCoMo 89.9%, "median 5% of context tokens used."+It now ships coding-agent front-ends too (Claude Code/Codex/Cursor/OpenCode+plugins + an **MCP server** with exactly three tools: `honcho_search`,+`honcho_chat`, `honcho_remember`), so it **collides with us on the shelf** — but+the thing remembered is fundamentally different: **Honcho remembers the *user*;+ai-memory remembers the *project*.** A coding team wanting cross-harness project+continuity would not switch to it (opaque DB, LLM-mandatory, user-centric,+multi-service), and an app builder wanting end-user personalization would not use+us — **adjacent, not a migration target either way**. Two ideas are worth+carrying forward as *optional LLM layers over* our zero-LLM core, never+requirements: the **dialectic/oracle query** (ask-a-question → synthesized+answer, which maps onto our retrieval as an opt-in LLM step) and the+**reasoning-tier ladder** (minimal→max reasoning per query as a clean+cost/quality knob). Deliberately **reject** the rest as off-mission: LLM-mandatory+ingestion, opaque-Postgres-as-truth, the Postgres+Redis+worker operational+weight, and the heavy theory-of-mind engine itself — a coding agent needs project+facts, decisions, and conventions, not a psychological model of the developer+(the lightweight "standing user preferences" slice we already have via global+scope is enough). Positioning note: preempt the inevitable "but Honcho scores 90%+on LongMemEval" by clarifying those are *user-recall* benchmarks on chat+transcripts, not *coding-project* recall — a different task we are not competing+on. Per the research-doc convention, Honcho has no standalone deep-dive; this+section is its record.+## 4. Research developments worth knowing- **"Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM@@ -413,6 +458,18 @@ benchmark number before R2 exists; chasing agentmemory's tool-countfounder). Hosted backend is closed-source, so its storage internals,latency, and benchmark numbers are vendor claims, not primary-verifiable.Analyzed inline in §3 per the no-standalone-doc convention.+- Honcho: github.com/plastic-labs/honcho (README, AGPL-3.0, ~7K stars,+ coding-agent integrations + MCP tools) and its in-repo CLAUDE.md+ (authoritative architecture: Postgres+pgvector/FTS, Redis, Deriver/+ Dreamer/Dialectic, peer `(observer, observed)` collections, LanceDB/+ Turbopuffer); honcho.dev/docs + docs.honcho.dev (peers, representations,+ dialectic endpoint); plasticlabs.ai/blog/research/Benchmarking-Honcho ++ evals.honcho.dev (vendor self-reported LongMemEval/LoCoMo/BEAM numbers,+ 2025-12-19); panews.io $5.35M pre-seed coverage (+ decentralized-identity+ roadmap, absent from the repo); andrew.ooo independent review;+ hermes-agent.nousresearch.com Honcho integration. Benchmarks are+ vendor-reported and not independently reproduced. Analyzed inline in §3+ per the no-standalone-doc convention.- Zep/Graphiti: arXiv:2501.13956; getzep.com temporal-KG explainer;Neo4j "Graphiti: Knowledge graph memory for an agentic world".- Letta: "Is a Filesystem All You Need?" (letta.com blog, Aug 2025).