Catalog Systems Coding-agent memory Tabnine

Tabnine

https://docs.tabnine.com/main/administering-tabnine/managing-your-team/context-engine

Enterprise Context Engine builds a multi-dimensional knowledge graph from repos + CI/CD + PRs + tickets + docs at the org level. Individual completions stay session-scoped. Tabnine Agents (Nov 2025) adds team-shared agent context. Acquired by Tricentis (2026-07-30); Tricentis is integrating the Enterprise Context Engine into its Agentic Quality Engineering Platform, and tabnine.com now redirects to tricentis.com.

Acquired. acquired by Tricentis Source · Alternatives and migration notes →

Acquired · Verified 2026-10-29 · fresh as of 2026-10-29 · 42 cited facts, 8 with a third-party source · 2 recorded changes · Suggest a correction

At a glance

Type
Org-level Context Engine + Tabnine Agents vendor fix
Tier
T2
Section
Coding-agent memory
Created
2023-11 third-party fix
Latest release
not applicable — not OSS fix
License
not applicable — not OSS fix
GitHub
not applicable — no GitHub repo fix
Pricing
No free tier; Code Assistant $39/user/mo, Agentic Platform $59/user/mo (annual); Headless Agents add-on $1.2k–5k/mo third-party fix
Funding
Acquired by Tricentis (2026-07-30); prior $25M Series B · 2023-11 third-party fix
Freshness
2026-10-29 fix
Layer
agent-infra repo fix
Licensing
commercial third-party fix
Deployment locus
ide vendor fix
Platform vs product
product vendor fix
Protocols
mcp-client vendor fix

Memory taxonomy

storage
graph
retrieval
graph-traversal
persistence
long-term
update
extraction
unit
document
governance
opaque
conflict
none

When to use

Optimised for: enterprise privacy + org-level Context Engine

Anti-fit: not for non-coding tasks

Pros & cons

Pros

Long-running enterprise coding assistant with on-prem option; memory respects enterprise data boundaries.

Cons

Slower model adoption than newer entrants; on-prem deployment is heavyweight.

Claims & capabilities

Cross-session memory only on enterprise tier (org-level).

Technical surface

API surface
not applicable — IDE plugin
Backend storage
custom
Deployment
Both
Embedding model
locked
Multi-tenancy
Deployment options: protected SaaS / single-tenant SaaS / VPC / on-prem Kubernetes / fully air-gapped
MCP
yes — Tabnine Agent in IDE (VS Code/JetBrains) and Tabnine CLI connect to stdio/HTTP/SSE MCP servers via mcpServers in settings.json or `tabnine mcp add`
A2A
searched not found
OpenTelemetry
searched not found

Alternatives to Tabnine → live options ranked by shared design, licence, hosting and MCP support

Similar systems

Other coding-agent memory in the catalog, ranked by inbound references.

  • Devin (Cognition) T1

    Structured Knowledge items stored server-side. Three-tier scope: repo-pinned (always injected), global (recall by relevance), org/enterprise (visible to org members). Auto-generates Repo Knowledge from repo structure each session; reads past session trajectories for self-improvement; writes notes for recurring scheduled tasks.

  • Aider T2

    Appends conversation turns to .aider.chat.history.md in project root. restore_chat_history defaults to false — no automatic replay into new sessions. Community /session save command for JSON state snapshots. .aider.conf.yml carries static preferences.

  • Augment Code T1

    Real-time knowledge graph indexed from connected repos + commit history + CI/CD + tickets + docs. Separate Agent Memory layer (Sept 2025) captures session decisions/corrections/goals as discrete items with developer review/approval UI. MCP endpoint exposes the graph. Acquired by Harness (2026-10-08): Harness bought select Augment Code assets, including Cosmos, the Auggie CLI and the Context Engine, and the team joined Harness. augmentcode.com now leads with Cosmos, a software-factory agent platform.

  • Letta Code T3

    Letta's stateful coding-agent harness: agents rewrite their own memory blocks and skills, version context in git via MemFS (syncable to GitHub) and reflect via a periodic /sleeptime 'dreaming' process. from Letta (MemGPT) team. letta-ai/letta-code is now the main Letta source (harness, terminal UI, App Server, channels); the Letta V1 API server was retired to the archive branch of letta-ai/letta.

  • Replit Agent T1

    No documented built-in persistent semantic memory store. Session duration expanded to 200 min (Agent 3); Agent 4 shifts toward persistent runtimes. Temporal used for orchestration durability, not semantic memory. Cross-session memory relies on filesystem + agent-written notes.

  • agentmemory (rohitg00) T3

    Self-hosted persistent memory layer that captures coding-agent activity and recalls it in later sessions, positioned on public benchmark results. #7 in TeleAI Awesome-Agent-Memory

Sources (41 cited facts, 8 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-29
    • Homepage “https://docs.tabnine.com/main/getting-started/context-engine” → “https://docs.tabnine.com/main/administering-tabnine/managing-your-team/context-engine”
    • Funding / ownership “$25M total Series B · 2023-11” → “Acquired by Tricentis (2026-07-30); prior $25M Series B · 2023-11” source
    #338
  2. 2026-10-22
    • Pricing “Free + paid” → “No free tier; Code Assistant $39/user/mo, Agentic Platform $59/user/mo (annual); Headless Agents add-on $1.2k–5k/mo” source
    • MCP support “searched not found — no public MCP support documented as of 2026-05” → “yes — Tabnine Agent in IDE (VS Code/JetBrains) and Tabnine CLI connect to stdio/HTTP/SSE MCP servers via mcpServers in settings.json or `tabnine mcp add`” source
    #219