Head to head · Agent frameworks · October 2026 research run

LlamaIndex Framework vs Terse Durable Actors

LlamaIndex Framework scores 73.8 (BB) on agent readiness against Terse Durable Actors's 69.6 (B), and leads in 4 of 7 scored categories. Terse Durable Actors leads on agent ergonomics and maintenance & community. Both do agent frameworks.

Best agent frameworks and SDKs · All 190 frameworks comparisons

Which one, for what

LlamaIndex Framework BB

Best for Python teams building retrieval-heavy agents over their own data, with many connectors.

Ahead on

  • Reliability, 70 against 51
  • Security & auth, 74 against 49
  • Transparency & trust, 67 against 53

Also in its favour

  • Agent-ready, a grade of BB or better
  • No key needed to call it

Watch for

Core is 0.14.x, and minor versions such as 0.13 and 0.14 carried breaking changes

Terse Durable Actors B

Best for Stateful actors for chat, collaboration and multi-agent coordination, as an open-source alternative to Cloudflare Durable Objects per its README.

Ahead on

  • Agent ergonomics, 89 against 73
  • Maintenance & community, 83 against 69

Also in its favour

  • Free to start without a card

Watch for

Version 0.18.7, with no stable release and no changelog file in the repository

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Security & auth LlamaIndex Framework +25

LlamaIndex Framework 74

Framework reading (telemetry defaults, approvals, guardrails, sandboxing). No telemetry found in llama-index-core (25). Human-in-the-loop events in Workflows and agents can wait for a person, but there's no per-tool approval primitive and CodeActAgent's executor is the developer's to supply (12). The threat model puts input validation on the application, with no prompt-injection guidance in the agent pages (5). Instrumentation events and callback handlers for tracing (14). A huntr bug bounty, GitHub private reporting and public advisories with fixed versions (18). 25+12+5+14+18 = 74.

Terse Durable Actors 49

One server secret, DURABLE_ACTORS_SECRET, as a bearer token for the API and MCP, plus an optional invoke-only key limited to public actor methods. With the secret unset the API is unauthenticated, which SECURITY.md warns about (15 of 30). The invoke-only key and the MCP read-only hints give some least privilege, with no confirmation step before invoke_actor (10 of 20). The OpenAPI file marks actor output as untrusted and to be rendered as plain text, with no guidance for agents on injected instructions (6 of 15). Request history, actor logs, WebSocket sessions and state versions tied to the request that saved them (12 of 15). SECURITY.md gives a private reporting address, security@useterse.ai. No bug bounty, certification or published advisories found (6 of 20). On GKE the self-hosting guide runs actors in gVisor sandbox pods with per-actor storage credentials. Total 49.

Reliability LlamaIndex Framework +19

LlamaIndex Framework 70

Local-package reading. Official PyPI packages with Python 3.10 to below 4.0 (20). Public unit-test, type-check, lint, coverage and CodeQL workflows, with the type-check, lint and CodeQL runs on main passing on 3 November (25). 379 open issues and 1,291 open issues and pull requests on 6 November, with 241 issues opened in the 90 days to 3 November. Of the 50 newest, 28 had a comment and 3 were closed; a stale bot and an issue classifier run on the repository (12). A dated, generated changelog per package, but core is 0.x and minors such as 0.13 and 0.14 carried breaking changes (8). Core isn't 1.0; Workflows is at 2.x, so partial (5). 20+25+12+8+5 = 70.

Terse Durable Actors 51

Graded as local software, the runtime and SDKs you run yourself. The README and the Python SDK README install with bunx durable-actors or uvx --from 'durable-actors[cli]' and state Bun 1.4.2+ and Python 3.11+, and the release workflow publishes to npm. The registry pages were not read (15 of 20). A public CI workflow runs Rust, Python, TypeScript and example builds on every push and pull request. Whether it passes on main was not checked (15 of 25). 23 issues were open on 18 November 2026, mostly improvements and feature requests, with a few bug reports such as a constructor that keeps its SQLite writes after throwing (17 November) and alarms that run more than once (11 November) (18 of 25). Release notes are generated from pull-request labels on GitHub Releases, which were not read, and no changelog file or breaking-change notes were found in the repository (3 of 15). Version 0.18.7, not 1.0 or declared stable (0). Total 51.

Agent ergonomics Terse Durable Actors +16

LlamaIndex Framework 73

Framework reading. MCP tools through a separate llama-index-tools-mcp package, with allowed tools selectable (18). Memory token limits, iteration caps and streaming events (16). Tool errors returned to the agent, with few typed errors (12). Workflow context serialises and resumes, and the DBOS package makes runs durable (16). Few required parameters, but OpenAI is the silent default for LLM and embeddings, Python here with a separate TypeScript edition (11). 18+16+12+16+11 = 73.

Terse Durable Actors 89

Ten MCP tools with one-line descriptions (25). Cursor paging with stated limits (1 to 100, or 1 to 500 for requests) and filters by actor, outcome, log level, text and time window (20). Errors carry a code and a message, start limits return named codes with Retry-After, and invalid MCP input says which characters are allowed (14 of 20). Nine tools carry readOnlyHint and invoke_actor carries destructiveHint, but invocations have no idempotency key (15 of 20). Local development needs one command and no credential, with official TypeScript and Python SDKs and generated typed clients (15). Total 89.

Maintenance & community Terse Durable Actors +14

LlamaIndex Framework 69

llama-index-core 0.14.25 on 21 September 2026, 46 days before this check (20). Two core changelog entries in the 90 days (19 August and 21 September), with integration packages and Workflows (2.24.1 to 2.26.1) publishing in between, so partial (12). 379 open issues and 1,291 open issues and pull requests on 6 November, with 241 issues opened in the 90 days to 3 November. Of the 50 newest, 28 had a comment and 3 were closed; a stale bot and an issue classifier run on the repository (12). Core, Workflows and integrations are current (15). CI and CodeQL passing on main and a stale-package policy that moves unmaintained integrations out of main (10). 20+12+12+15+10 = 69.

Terse Durable Actors 83

v0.18.7 tagged on 18 November 2026, the day of the check (30). 118 tags since v0.1.0 on 2 September 2026, with eight between 15 and 18 November (20). 23 open issues, three of them with long threads (7, 9 and 15 replies) and most with none. Pull requests from five outside contributors were merged between 2 October and 3 November 2026, and CONTRIBUTING.md says GitHub issues are triaged into the team's tracker (10 of 25). Current official TypeScript and Python SDKs at 0.18.7. The MCP endpoint is self-hosted and not in the official registry, which was not searched (15). CI with pinned action versions and lockfiles for Bun, Cargo and uv (8 of 10). Total 83.

Transparency & trust LlamaIndex Framework +14

LlamaIndex Framework 67

MIT (30). The library stores nothing itself; OpenAI is the default provider unless changed, which the docs show (20). A stale-package policy and removals noted in the changelog, such as deprecated IPEX integrations removed in 0.14.25, without dated notice (10). No telemetry, though no page states it (12). 30+20+10+12 = 72.

Terse Durable Actors 53

MIT, copyright 2026 Terse (30). Self-hosted state stays in your PostgreSQL database and GCS bucket per the self-hosting guide. Terse's terms and privacy policy, both dated 14 May 2026, describe an earlier product of flows and workspaces, give no retention periods and don't mention Terse Cloud (10 of 30). No deprecation policy found, and SECURITY.md says older releases get no backports (0 of 20). SDK invocation telemetry is off by default and writes to standard error when enabled, and request spans and platform events are exported only to a collector the operator configures. No call to Terse's own hosts was found in the runtime or SDK source (18 of 20). Total 58.

Score by category

CategoryWeightLlamaIndex FrameworkTerse Durable ActorsEdge
Reliability16%7051LlamaIndex Framework +19
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8581LlamaIndex Framework +4
Agent ergonomics13%7389Terse Durable Actors +16
Security & auth14%7449LlamaIndex Framework +25
Payments & pricing10%9090even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6983Terse Durable Actors +14
Transparency & trust7%6753LlamaIndex Framework +14
Negative events≤15-20
TotalBB 73.8/100B 69.6/100

Facts side by side

FactLlamaIndex FrameworkTerse Durable Actors
KindAgent frameworkAgent framework
VendorLlamaIndexTerse
Hosted endpointno (local only)no (local only)
TransportsStreamable HTTP
AuthNoneAPI key
PricingFreeFreemium
x402nono
LicenceMITMIT
Tools exposednone10
Read-only variant documentednono
llms.txtyesyes
Last release2026-09-212026-11-18
Terms last updatedno document linked2026-05-14
Privacy policy last updated2026-08-242026-05-14
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetyes
Terms restrict benchmarkingnot read yetnot found in the text
Terms or service can change without noticenot read yetyes
Arbitration or class-action waivernot read yetnot found in the text
Popularity53k stars, 1.3M PyPI/wk368 stars

How the scores have moved

Verdicts

LlamaIndex Framework

An MIT Python framework for retrieval and agents, with three agent types, multi-agent AgentWorkflow, resumable event-driven Workflows, MCP tools and a huntr bug bounty, and no telemetry found. Core is still 0.14 with breaking minors, OpenAI is the silent default, and approval and injection handling are left to the application.

Terse Durable Actors

Durable Actors gives coding agents ten compact MCP tools with read-only and destructive hints, a public OpenAPI 3.1 file and typed TypeScript and Python clients, under MIT with near-daily releases. It is pre-1.0 at 0.18.7, one server secret controls everything unless an invoke-only key is added, and Terse's policies predate Terse Cloud.

Before you call either

LlamaIndex Framework

  1. Set Settings.llm and Settings.embed_model explicitly so calls don't go to OpenAI by default
  2. Install llama-index-tools-mcp for MCP tools and pass only the allowed tools the task needs
  3. Use Workflow human-in-the-loop events before tools that write or send
  4. Pin llama-index-core to a minor version, since minors have broken APIs
  5. Upgrade llama-index-core to 0.13.0 or later to clear the 2025 advisories

Terse Durable Actors

  1. Call list_projects first and pass its projectId to every other tool
  2. Never retry invoke_actor when the outcome is unknown, because calls are not deduplicated and run real code
  3. Set DURABLE_ACTORS_SECRET before exposing a server beyond localhost, and send it as a bearer token
  4. Give backends that only call actors the invoke-only key, not the server secret
  5. On 429 actor_start_rate_limited, wait for the Retry-After seconds before starting another actor

Questions

Which is better for AI agents, LlamaIndex Framework or Terse Durable Actors?

LlamaIndex Framework scores 73.8 (BB) on agent readiness against Terse Durable Actors's 69.6 (B), and leads in 4 of 7 scored categories. Terse Durable Actors leads on agent ergonomics and maintenance & community.

Are LlamaIndex Framework and Terse Durable Actors open source?

Yes. LlamaIndex Framework is open source (MIT). Terse Durable Actors is open source (MIT).

Other comparisons with LlamaIndex Framework or Terse Durable Actors

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.