Skip to content

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.md
index 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.md
index 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 basics
and 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 tool
behavior hints (readOnly/destructive/idempotent) on the 23-tool surface; a
clustering/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-encoder
reranking + Teams tier; `research-agentmemory.md` says 53 tools / 124 endpoints
diff --git a/docs/research-2026-landscape.md b/docs/research-2026-landscape.md
index 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 worth
borrowing (see R8). Per the research-doc convention, Supermemory has no
standalone 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-count
founder). 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).